Reposted by Karim KnaebelZhenjun Zhao @ericzzj.bsky.social · 01/06/2026SurGe: Improved Surface Geometry in Point Maps @karimknaebel.bsky.social, Gonzalo Martin Garcia, Christian Schmidt, @ifradlin.bsky.social, Lucas Nunes, @dcdegeus.bsky.social, Bastian Leibe arxiv.org/abs/2605.31577 253
Karim Knaebel @karimknaebel.bsky.social · 14/05/2026I think it’s important to have a policy, and actually enforce it in unambiguous cases. This is separate from finding these cases. You won’t find all of it, but at least when such a case is revealed by eg auto flagging bogus references, user reports, or coincidence, there is a policy in place. 010
Karim Knaebel @karimknaebel.bsky.social · 13/05/2026Bravo! arXiv soon stricter than major ML conferences? 😁 110
Karim Knaebel @karimknaebel.bsky.social · 04/05/2026kk thx! yes, I also think so, but then I couldn't actually find this explicitly stated anywhere. 110
Karim Knaebel @karimknaebel.bsky.social · 04/05/2026@neuripsconf.bsky.social will we still be able to change the abstract and title after the abstract deadline? 100
Karim Knaebel @karimknaebel.bsky.social · 23/02/2026Do you also add a short cooldown phase after the constant part? I believe for self-supervised representation learning you don’t want to cool down, but for downstream tasks it usually gives a big boost. 010
Karim Knaebel @karimknaebel.bsky.social · 08/02/2026were cvpr reviews ever public since this motion? 110
Karim Knaebel @karimknaebel.bsky.social · 30/01/2026I ran the first frame through an (undertrained) internal monocular model. When you zoom in, you can see the tree and street for scale. The clouds still seem too small though; only about 42x the size of the tree in the foreground. 040
Karim Knaebel @karimknaebel.bsky.social · 10/11/2025Those are awesome, thanks for the inspiration 030
Karim Knaebel @karimknaebel.bsky.social · 30/09/2025So you uv sync -p 3.13 the first time (if you care about the exact version), and then you never need to pass it again. The existing venv “soft pins” its python version until you explicitly request a different version, either via CLI or updated constraints of the python version. 030
Karim Knaebel @karimknaebel.bsky.social · 30/09/2025I use it all the time, super useful :) It won’t pin, just makes sure your venv uses this python version if it doesn’t already or doesn’t exist yet. 100
Karim Knaebel @karimknaebel.bsky.social · 29/09/2025What’s the reason for pinning in general? I somehow never found a use case for it. If I want a specific version from that range, I provide it in uv sync on demand. 100
Karim Knaebel @karimknaebel.bsky.social · 21/09/2025Very good read, thanks for writing this up :) 010
Karim Knaebel @karimknaebel.bsky.social · 10/09/2025Does it still happen when you compile before DDP? I always use DDP as the outermost wrapper, there is too much hacky stuff going on in its forward and backward for my liking. 100
Karim Knaebel @karimknaebel.bsky.social · 25/07/2025The normal metrics in Tab. 1 also don’t match. I checked only for DSINE, and here the actual metrics are considerably better than in Tab 1. Also missing some sota normal methods. Tab 3 is only a small subset of common benchmarks, and on 1/2 of the datasets it’s worse than both VGGT and MoGe. 120
Karim Knaebel @karimknaebel.bsky.social · 21/07/2025Same, I don’t want to use them anymore now, and if I “have to”, then I’m writing them as triple dashes ---. At least semicolons are still safe 👀 000
Reposted by Karim KnaebelInternational Conference on 3D Vision @3dvconf.bsky.social · 01/07/2025Understanding and reconstructing the 3D world are at the heart of computer vision and graphics. At #CVPR2025, we’ve seen many exciting works in 3D vision. If you're pushing the boundaries, please consider submitting your work to #3DV2026 in Vancouver! (Deadline: Aug. 18, 2025) 1177
Karim Knaebel @karimknaebel.bsky.social · 17/06/2025In my mind, I often associate instance seg with fancy depth clustering. 020
Karim Knaebel @karimknaebel.bsky.social · 13/04/2025I like the look. DINOv2, DUSt3R, CroCo v2, and GB are misspelled if you want to fix those. 110
Karim Knaebel @karimknaebel.bsky.social · 10/04/2025I haven’t experienced that yet, but I’m not sure if I’ve tried on that many files. Which one did you try: `dua a` (or just `dua`) will block and finally print, which can take a long time. `dua i` starts an interactive TUI and loads everything in the background while you can already start inspecting. 000
Karim Knaebel @karimknaebel.bsky.social · 10/04/2025Looks good. I haven’t seen it before. Can also recommend this one: github.com/Byron/dua-cligithub.comGitHub - Byron/dua-cli: View disk space usage and delete unwanted data, fast.View disk space usage and delete unwanted data, fast. - Byron/dua-cli 210
Reposted by Karim KnaebelDavid Picard @davidpicard.eurosky.social · 21/03/2025🔥🔥🔥 CV Folks, I have some news! We're organizing a 1-day meeting in center Paris on June 6th before CVPR called CVPR@Paris (similar as NeurIPS@Paris) 🥐🍾🥖🍷 Registration is open (it's free) with priority given to authors of accepted papers: cvprinparis.github.io/CVPR2025InPa... Big 🧵👇 with details! 713652
Karim Knaebel @karimknaebel.bsky.social · 04/04/2025Ah yes, you’re right, thanks for the reference! It’s really just a line in space without explicitly specifying a point on the line as its origin. 000
Karim Knaebel @karimknaebel.bsky.social · 04/04/2025The origin is not lost though, it’s just encoded differently. In the end it’s still 6 dims, 3 for the direction and 3 for the origin. A bit unclear to me though what benefit this origin encoding brings. 100
Karim Knaebel @karimknaebel.bsky.social · 04/04/2025Their proposed architecture only makes sense for a dense parameterization. I don’t think they ablate with other dense representations though. 010
Karim Knaebel @karimknaebel.bsky.social · 04/04/2025Correction: the origin is already encoded in the Plücker ray. I meant that DiffusionSfM encodes /both/ origin and endpoint. 010
Karim Knaebel @karimknaebel.bsky.social · 04/04/2025I think the first time I saw Plücker rays was in the Camera as Rays paper arxiv.org/abs/2402.14817. The same authors also recently released DiffusionSfM, where they indeed keep the origins o as well.arxiv.orgCameras as Rays: Pose Estimation via Ray DiffusionEstimating camera poses is a fundamental task for 3D reconstruction and remains challenging given sparsely sampled views (<10). In contrast to existing approaches that pursue top-down prediction of gl... 210
Karim Knaebel @karimknaebel.bsky.social · 30/03/2025Agree, einops or shape in comments is a must. Also, makes it much easier for others to read and understand the code without executing it. 000
Karim Knaebel @karimknaebel.bsky.social · 20/03/2025Maybe last one, could you try VGGT single-view on that image for direct comparison? 😁 100
Karim Knaebel @karimknaebel.bsky.social · 20/03/2025True. Does MoGe do a better job at segmenting the sky here? 100
Karim Knaebel @karimknaebel.bsky.social · 20/03/2025Hmm yes, not sure if the demo is bugged or if it didn’t correctly segment the sky 🤔 Do you have access to GPUs to test this locally? 100
Karim Knaebel @karimknaebel.bsky.social · 20/03/2025Feels more native than a separate mask prediction as with MoGe. Then again, could turn out to be better not to mix up the concepts of confidence and undefinedness even though they seem related. 110
Karim Knaebel @karimknaebel.bsky.social · 20/03/2025Ah yes, now I get it. Detecting sky is usually not part of the benchmarks. 000
Karim Knaebel @karimknaebel.bsky.social · 20/03/2025There is no supervision for specific confidence values though, if that’s what you meant. 100
Karim Knaebel @karimknaebel.bsky.social · 20/03/2025The depth loss is scaled by the confidence and the sum of confidences is added as a regularization term, otherwise the model just predicts all-zero confidence and gets a perfect loss. 100
Karim Knaebel @karimknaebel.bsky.social · 20/03/2025The cleanest way would probably be to force the model to predict zero confidence for sky pixels, but still mask both the sky-pixel confidence and depth values from the other losses. 110
Karim Knaebel @karimknaebel.bsky.social · 20/03/2025Regressing huge values close to inf is hard/impossible to do with these model architectures and will make training unstable. I think masking inf values during training and eval makes sense. For inference w/o GT either a separate segmentation model, or predicting a mask as in MoGe is perfectly fine. 210
Karim Knaebel @karimknaebel.bsky.social · 20/03/2025They use an of-the-shelf sky segmentation method. 010
Karim Knaebel @karimknaebel.bsky.social · 20/03/2025Benchmarks also ignore sky pixels; otherwise, what would you say should be the correct target for these in a benchmark? 110
Karim Knaebel @karimknaebel.bsky.social · 19/03/2025How does it look with sky pixels masked out in the output? I think I read that sky pixels are undefined outputs in VGGT, because they’re excluded from the loss. 200
Reposted by Karim KnaebelJianyuan Wang @jianyuanwang.bsky.social · 17/03/2025Introducing VGGT (CVPR'25), a feedforward Transformer that directly infers all key 3D attributes from one, a few, or hundreds of images, in seconds! Project Page: vgg-t.github.io Code & Weights: github.com/facebookrese... 34614