5 citations · 15 across the 41 of their papers we have counts for
17 papers · 1 filter
VFMF: World Modeling by Forecasting Vision Foundation Model Features
Gabrijel Boduljak, Yushi Lan, Christian Rupprecht +1
Forecasting from partial observations is central to world modeling. Many recent methods represent the world through images, and reduce forecasting to stochastic video generation. A…
Particulate: Feed-Forward 3D Object Articulation
Ruining Li, Yuxin Yao, Chuanxia Zheng +4
We introduce Particulate, a feed-forward model that, given a 3D mesh of an object, infers its articulations, including its 3D parts, their kinematic structure, and the motion const…
What Happens Next? Anticipating Future Motion by Generating Point Trajectories
Gabrijel Boduljak, Laurynas Karazija, Iro Laina +2
We consider the problem of forecasting motion from a single image, i.e., predicting how objects in the world are likely to move, without the ability to observe other parameters suc…
AutoPartGen: Autogressive 3D Part Generation and Discovery
Minghao Chen, Jianyuan Wang, Roman Shapovalov +6
We introduce AutoPartGen, a model that generates objects composed of 3D parts in an autoregressive manner. This model can take as input an image of an object, 2D masks of the objec…
Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey
Jiahui Zhang, Yuelei Li, Anpei Chen +15
3D reconstruction and view synthesis are foundational problems in computer vision, graphics, and immersive technologies such as augmented reality (AR), virtual reality (VR), and di…
Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos
Vadim Tschernezki, Diane Larlus, Iro Laina +1
Computer vision is largely based on 2D techniques, with 3D vision still relegated to a relatively narrow subset of applications. However, by building on recent advances in 3D model…
VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory
Runjia Li, Philip Torr, Andrea Vedaldi +1
We propose a novel memory module for building video generators capable of interactively exploring environments. Previous approaches have achieved similar results either by out-pain…
Triangle Splatting for Real-Time Radiance Field Rendering
Jan Held, Renaud Vandeghen, Adrien Deliege +7
The field of computer graphics was revolutionized by models such as Neural Radiance Fields and 3D Gaussian Splatting, displacing triangles as the dominant representation for photog…
Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction
Weirong Chen, Ganlin Zhang, Felix Wimbauer +4
Traditional SLAM systems, which rely on bundle adjustment, struggle with highly dynamic scenes commonly found in casual videos. Such videos entangle the motion of dynamic elements,…
Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
Zeren Jiang, Chuanxia Zheng, Iro Laina +2
We introduce Geo4D, a method to repurpose video diffusion models for monocular 3D reconstruction of dynamic scenes. By leveraging the strong dynamic priors captured by large-scale…
Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better
Zihang Lai, Andrea Vedaldi
Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution,…
SynCity: Training-Free Generation of 3D Worlds
Paul Engstler, Aleksandar Shtedritski, Iro Laina +2
We address the challenge of generating 3D worlds from textual descriptions. We propose SynCity, a training- and optimization-free approach, which leverages the geometric precision…
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction
Edgar Sucar, Zihang Lai, Eldar Insafutdinov +1
DUSt3R has recently shown that one can reduce many tasks in multi-view geometry, including estimating camera intrinsics and extrinsics, reconstructing the scene in 3D, and establis…
Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images
Tianhao Wu, Chuanxia Zheng, Frank Guan +2
Most image-based 3D object reconstructors assume that objects are fully visible, ignoring occlusions that commonly occur in real-world scenarios. In this paper, we introduce Amodal…
VGGT: Visual Geometry Grounded Transformer
Jianyuan Wang, Minghao Chen, Nikita Karaev +3
We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from…
DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness
Ruining Li, Chuanxia Zheng, Christian Rupprecht +1
Most 3D object generators prioritize aesthetic quality, often neglecting the physical constraints necessary for practical applications. One such constraint is that a 3D object shou…
Learning segmentation from point trajectories
Laurynas Karazija, Iro Laina, Christian Rupprecht +1
We consider the problem of segmenting objects in videos based on their motion and no other forms of supervision. Prior work has often approached this problem by using the principle…