10 papers
JtT: Rethinking Point Trajectory Diffusion for Diverse and Rigid Motion from an Image
Gabrijel Boduljak, Yushi Lan, Christian Rupprecht +1
We study forecasting rigid-body motion from a single image: generating diverse and physically plausible future trajectories for arbitrary points in a scene, without building rigidi…
SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion
Paul Engstler, Iro Laina, Christian Rupprecht +1
We present SynCity 3000, a framework for generating 3D scenes that are globally coherent while enabling fine-grained layout control. Building on the ability of current image-to-3D…
Syn4D: A Multiview Synthetic 4D Dataset
Zeren Jiang, Yushi Lan, Yihang Luo +8
Dense 3D reconstruction and tracking of dynamic scenes from monocular video remains an important open challenge in computer vision. Progress in this area has been constrained by th…
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…
AnimalClue: Recognizing Animals by their Traces
Risa Shinoda, Nakamasa Inoue, Iro Laina +2
Wildlife observation plays an important role in biodiversity conservation, necessitating robust methodologies for monitoring wildlife populations and interspecies interactions. Rec…
Industrial Synthetic Segment Pre-training
Shinichi Mae, Hirokatsu Kataoka, Ryousuke Yamada +3
Vision Foundation Models (VFMs) have made remarkable progress and are increasingly being applied to segmentation tasks in real-world industrial settings. However, VFMs pre-trained…
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…
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…
Rethinking Image Super-Resolution from Training Data Perspectives
Go Ohtani, Ryu Tadokoro, Ryosuke Yamada +7
In this work, we investigate the understudied effect of the training data used for image super-resolution (SR). Most commonly, novel SR methods are developed and benchmarked on com…
Scaling Backwards: Minimal Synthetic Pre-training?
Ryo Nakamura, Ryu Tadokoro, Ryosuke Yamada +6
Pre-training and transfer learning are an important building block of current computer vision systems. While pre-training is usually performed on large real-world image datasets, i…