Space Monkeys, Raw Video, and Giving Us All You've Got

The team at Magic Lantern have managed to hack the Canon 5D Mark III to record 14-bit raw 1080p video at 24 frames per second. The results are stunning—the highest-quality video we’ve seen from a DSLR yet, comparing favorably to images from cameras costing much more.

This is a big deal. But maybe not as big a deal as some have made it out to be. Like Ham, the chimpanzee that was launched into space on a Mercury rocket, the Magic Lantern raw hack is less notable for its discrete accomplishment than for what it portends.

How it Works

I was skeptical about the announcement of raw video at 1080p. This wasn’t a sensor crop, this was a full-frame image, somehow downsampled to 1920x1080—yet still being touted as “raw.”

How is this Magic Lantern thing “raw” if it’s scaled down from sensor res to 1080p? Scaling requires debayering. Debayered is not raw.

— Stu Maschwitz (@5tu) May 13, 2013

The answer came back from Magic Lantern themselves:

@5tu it’s not debayered, it’s 14-bit RGGB.

— Magic Lantern (@autoexec_bin) May 13, 2013

@5tu no idea, only Canon knows how the downsampling works. On 5D3 there’s no moire, on 5D2 there is.

— Magic Lantern (@autoexec_bin) May 13, 2013

Put this way, it makes sense—and matches what Magic Lantern said in their original post:

Key ingredients:

• canon has an internal buffer that contains the RAW data

Of course. Canon sparsely samples the sensor (the popular theory is that they skip lines and bin rows) to create their own 1080p bayer image, which they rapidly debayer to create 1080p video frames. It looks like Magic Lantern have found a way to grab this raw buffer and save it directly to the CF card.

Whatever magic Canon worked to eliminate the moiré in the 5D Mark III’s video now benefits Magic Lantern users as well. And whatever downsides there are to this sparse sampling will also affect the raw hack.

What it Takes

Right now, the hack requires quite a bit of work to get up and running, and even more work to derive useable results.

But those usable results are compelling. There are tremendous opportunities afforded by the raw video hack over the compressed H.264 recordings the camera natively makes.

• Post-processing debayering can be much better than the hasty in-camera processing. The much-lamented softness of 5D Mark III video is improved noticeably by handling the debayering (including noise reduction) after the fact. Although I can’t help but wonder if we’d get even better results from a demosaicing algorithm tuned to the specifics of the 5D’s subsampling pattern.
• The 14-bit raw frames contain a great deal of dynamic range that 8-bit, heavily compressed video does not.
• No compression.

But there’s a price to pay for recording 14-bit uncompressed raw. It requires crazy-fast CF cards, and you’ll only get 15 minutes of video on that 128 GB card, according to Cinema 5D, who graciously posted their workflow and samples, “after struggling for a day” to get it all working.

What it Means

Even once the setup process is streamlined, and the raw-to-DNG conversion process is streamlined (or eliminated), uncompressed raw video is probably not the best option for most DSLR shooters. Better would be something like ProRes or DNxHD—but that would require high-quality debayering in the camera, which would seem to require more processing power than the 5D Mark III has to offer. More processing means more heat, which means a very different camera design than an SLR. It’s easy to see why digital cinema cameras start to get expensive.

The 5D Mark III raw hack is cool. It’s important. It’s something we’ll use, and like, and get good results from. But as exciting as it is today, it’s even more significant for what it means for the future of low-cost digital cinema cameras.

Mr. Ham risked his furry life to prove that a primate could flip switches in space. Three months later, a human being took the same trip. By proving that raw video is possible from the 5D Mark III, Magic Lantern have joined the forces pushing the industry in an important new direction.

Five years ago I wrote that large-sensor video had shown “that it’s no longer OK for manufacturers to make a video camera that doesn’t excite us emotionally.” Since the industry did such a good job of heeding that advice, my new mandate for the future is this:

It’s no longer OK for cameras not to give us everything they’ve got.

What I love about the new generation of cameras, such as those from Blackmagic, Red, and even GoPro, is that they all give you everything they’ve got. They’ll give you the highest image quality they can, in the smallest package possible. They’ll compress images as much or as little as you want. They’ll max out their resolution at the expense of frame rate, or vise versa—whichever you like. And they’ll pack their best dynamic range into any format they can record.

Compared to this, Canon and Sony’s digital cinema product lines seem cruelly restricted at every tier. The result was palpable at NAB. As I said on stage at the SuperMeet, the show seemed to belong to camera upstarts. To cameras from small booths. From the Phantom Flex4K with its Super35 4K at 1,000 fps, to the Digital Bolex, the exciting cameras at every price point were the ones not charging by the button, feature, or codec, but simply giving you all they could do.

What Magic Lantern have done is show camera makers that if they won’t give us all they’ve got, we’ll just take it anyway. The smart manufacturers will try to beat us there out of the box.

Blackmagic Cinema Camera

The NAB 2012 announcement of the Blackmagic Cinema Camera (which folks are thankfully calling simply “the BMC”) from Blackmagic Design, the company that makes delightful video doohickies and acquired industry giants Da Vinci and Teranex, revealed a few interesting things:

• We are living in the “Chinese curse” age of cameras.
• In other words, disruption is the new norm. I’m not sure if there’s a static “game” to “change” anymore. So maybe we could all agree to stop saying that?
• Prolost is not a “camera blog.”

The so-called Chinese Curse goes “May you live in interesting times,” which certainly describes the landscape of digital cinema offerings available today. Apparently, we self-sufficient film folk now constitute a market worth serving directly. Where once we bent ill-suited cameras to our cinematic purposes (first all-in-one camcorders with tiny sensors and abusive automation, then DSLRs with near-accidental video functionality), now we can’t go a month without another “revolutionary” filmmaking camera competing to offer us something amazing at a previously unimaginably low price.

The question is, will these purpose-built offerings, such as the Kickstarter success Digital Bolex, the Sony FS–700, the 4K-ish Canon 1D C, and the KineRAW-S35 cure the DV Rebel of the urge to repurpose consumer cameras for their filmmaking efforts?

Blackmagic has seemingly (nearly) hit the “3k for 3k” target that many hoped Red would deliver, at a Micro–4/3-ish sensor size wandering between the 2/3” sensor many associated with the notion of a 3K raw camera and the increasingly ubiquitous and affordable Super 35mm size. If that seems like a decent deal, it’s worth noting that every BMC ships with full licenses of Resolve and UltraScope.

I was pretty busy when this camera was announced, but that’s not the only reason I refrained from comment at the time. I’ve gotten a bit weary of writing about unreleased cameras. Red has taught me to comb my writing for phrases like “the camera will have” and replace them with “the camera is said to feature,” and pretty soon I feel like I’m writing about nothing. But late last night, cinematographer John Brawley posted five test shots from a “production model” of the BMC to a brand-new Blackmagic forum. Brawley encouraged us to download the Cinema DNG sequences ourselves and have a play—so I did.

I love big-sensor digital cinema. I love shallow depth-of field. I’m fond of pointing out that sex appeal trumps tech specs every time. The interesting thing about the footage from this not-quite-cinema-sized sensor is that it is sexy. Not because of fetishistically shallow depth-of-field (although Brawley handily demonstrated that focus control is eminently possible with the BMC and some nice glass), but because it’s raw. I graded these shots in Lightroom 4. They came in looking a touch overexposed. I easily recovered the highlights and pushed these shots all over the place, but they never broke. After years of shooting with Canon HDSLRs to massively-compressed codecs, the rich neg offered by this little camera was beyond refreshing.

It’s easy to imagine that Blackmagic chose the smaller sensor to keep the price of the BMC down. It’s easy to get caught up thinking that maybe next, they’ll release a true Super 35 version of this rig. Or that the KineRAW at $6K might be worth the extra cost over the BMC.

But the challenge that befalls camera manufacturers is not to build the “perfect” digital cinema camera. It’s to capture the hearts and minds—and wallets—of filmmakers as much, or even more, as the wrong camera for the job keeps doing.

I think the Blackmagic Cinema Camera might just do that.

The Blackmagic Cinema Camera is available for pre-order now from B&H.

I'm Back

Sorry for the long radio silence. Here’s what I’ve been up to.

In early April I traveled to Montreal to direct a Canadian Lysol commercial for Euro RSCG NY. If you live in Canada and have tried to view a web video recently, you may have already been forced to watch it. When I get my director’s cut done, I’ll post it. We shot on the Alexa, and it marked my first opportunity to direct for Bodega, a production company run by some old friends with whom I’m delighted to be working.

I then flew directly to Toronto to help my friend Scott Stewart with a very exciting new project. Scott was invited to direct the pilot of a new Syfy series called Defiance. The show, developed simultaneously with a Massively Multiplayer Online game from Trion Worlds, was so enormous in scope that Scott lobbied for me to be brought on as “Additional Units Producer.” Terminology in TV is a little different than in features, but the role was very similar to my second unit directing duties on The Spirit. For just over four weeks I shadowed Scott with my mini “splinter unit” crew, picking up inserts and sometimes even entire scenes of this epic show. Scott and his cinematographer Attila Szalay chose the Epic for the pilot, although one of our three camera bodies was a Scarlet. We almost never cared which was which. I met some amazing new friends, learned a ton, and, as you may have noticed, didn’t have much time for Twitter or blogging.

My sudden streak of back-to-back work overlapped with NAB and its aftermath, leaving some to speculate that my silence on certain camera and other filmmaking tech announcements held some portent. People were drawing all sorts of conclusions, none of which were true. Maybe I was testing a new camera and sworn to secrecy? Maybe I was snubbing certain tech intentionally?

The only accurate conclusion, and the one that seemed most obvious to me, was one at which no one arrived:

This is not a camera blog.

There are plenty of wonderful blogs out there that exhaustively and reliably cover every new camera, every new piece of filmmaking tech. You read them every day, and so do I. We can all be grateful for them. But I hope you see a difference between those sites and this one.

This difference must not be as obvious to some as it is to me. I’m always amused when I receive a kind message to the effect of “I can’t wait for you to review this new camera!” Looking back through the archives, I don’t believe I’ve ever “reviewed” a camera.

I do write a lot about cameras. I also write about screenwriting, post-production, and other filmmaking things. Sometimes I write about tasty beverages. This blog is not my work. It’s a reflection of my work. It’s me learning out loud. And I’m always thrilled and honored when you enjoy it.

The Passion of the Bolex

My last post focussed on some concerns and questions I had about the Digital Bolex Kickstarter campaign. Despite stating numerous times that “I really want these guys to win,” I didn’t spend much time talking about what I liked about their project—and have thus unwittingly been cast as a vicarious mouthpiece for some far more negative appraisers than myself.

I could have mentioned that I appreciate any camera concept that sets out to capture the highest-quality image and bring it home unadulterated. I could have pointed out the planned on-board XLR inputs and metal construction. I could have talked up the compact size, or the affordable price. I could have cast these positives against the embarrassing backdrop of expensive, brick-shaped cameras made of cheap plastic that hammer your footage into an over-compressed pulp before committing it to a CF card, offered by camera companies with high-end markets to protect.

But all that stuff now pales against my new favorite thing about the Digital Bolex: how its creators reacted to my blog post.

Three days after launching their campaign, which funded successfully in less than 24 hours and has now well exceeded its outside target of $250,000, who do the Digital Bolex creators want to talk to? The grumpy guy who posted a bunch of concerns and tough questions.

Elle was a good sport about my post right away on Twitter, but Joe also sought me out via the Prolost contact form. We had a delightful chat this morning via phone. Joe specifically wants to connect with filmmakers who have reasonable concerns. He sees thoughtful critique as an opportunity, not an attack.

You know, like all our favorite camera makers.

Joe is so mellow in the Kickstarter video that I was immediately taken aback by how enthusiastic and passionate he was on the phone. He and his partners have an idea that seems so simple to them that he’s shocked they’re (nearly) the only ones doing it. Here’s some of what we talked about:

• The reason Joe feels they can make this camera at the price they’ve set is that it is the simplest possible digital camera—just a sensor and a card slot, with the bare minimum of electronics in between. He points out rightly that the D16 needs to do far less than any of the many far less expensive video cameras out there. A $200 flip camera requires more processing power than what they’ve envisioned, because it needs to debayer, color-space-convert, and compress the footage in real time.

• Joe harkened back to the days of the original Bolex and other 16mm film cameras, when the camera “didn’t affect the image quality at all, it just carried the film.” “[The Digital Bolex] is just the carrier between the sensor and the card.”

• Joe’s other passion is about on-set monitoring and the ubiquitous flip-out LCD panel on digital video cameras. He hates them—or rather, hates that they’ve taken the trust away from the director/cinematographer relationship. The director sees the ugly little image and thinks that’s what their movie is going to look like, instead of listening to the DP. “That little LCD has robbed the independent film industry of cinematography.”

• If there’s one criticism Joe’s sick of hearing, it’s “If Red couldn’t do it, how can these guys?”—a chorus of which I must confess to being a part. Of course, the situation is more nuanced than that. Red was aiming for an integrated, electronic zoom lens at that price point, as well as all the powerful internal computing horsepower required to compress Redcode footage.

  Ultimately, it seems clear to me that Red chose not to pursue the 3K Scarlet rather than “failed” to deliver it. “We recently came to the conclusion that, indeed, we cater to the professional market,” wrote Jim Jannard. “We want to build the best tools possible for those that want to ‘man up.’ Life is short and the clock is ticking.”

• Amazingly, Joe expressed the same sentiment, but carried it in a much different direction: “You only have so much time in this life,” he said to me. “I want to spend mine having fun.” I can think of no better expression of the difference between Digital Bolex’s lofty camera promises and Red’s.

• They’re not kids building these cameras in a garage. They have manufacturing partners who know how to bring camera stuff to market.

• I asked Joe about the 4:4:4 descriptor on their site. He said it was pulled directly from Kodak’s documentation of the CCD sensor, and that he realizes it’s misleading in the context of a raw workflow.

• Joe has a background in image software and is very interested in debayering techniques. He’s researching how to provide the best quality 1:1 2K RGB renderings of the D16’s raw DNG files. Now that they’ve hit the $250K mark, raw processing software is a part of what they plan on delivering to their backers.

• But the Digital Bolex also lists JPEG and TIFF output, so real-time debayering is in the plans. Joe estimates that a high-quality JPEG frame could be about 1/3 the size of a DNG frame.

Unlike some seem to, I get no joy from fearing the worst about a project like this. I wasn’t very happy about writing Tuesday’s post, and while most of you got it, the easily-inferred negativity that I tried to dampen with honest optimism was enough to bring the internet to my door, resulting in my first opportunity in months to delete a couple of nasty comments.

Now I’m glad I wrote what I did though, because, as a result, I have a new friend who makes cameras. Thanks for taking the time Joe, and a hearty congratulation and best of luck to you and the Digital Bolex team. Maybe some of my readers will ask themselves the same question I posed to myself: In your short time on this Earth, would you rather be a pessimist and be proven right? Or an optimist who’s occasionally wrong?