Related papers: Perception-as-Control: Fine-grained Controllable I…
Robotic manipulation tasks often rely on static cameras for perception, which can limit flexibility, particularly in scenarios like robotic surgery and cluttered environments where mounting static cameras is impractical. Ideally, robots…
Detecting and recognizing objects interacting with humans lie in the center of first-person (egocentric) daily activity recognition. However, due to noisy camera motion and frequent changes in viewpoint and scale, most of the previous…
Analyzing human motion is a challenging task with a wide variety of applications in computer vision and in graphics. One such application, of particular importance in computer animation, is the retargeting of motion from one performer to…
In recent years, video generation has seen significant advancements. However, challenges still persist in generating complex motions and interactions. To address these challenges, we introduce ReVision, a plug-and-play framework that…
Visual navigation using only a single camera and a topological map has recently become an appealing alternative to methods that require additional sensors and 3D maps. This is typically achieved through an "image-relative" approach to…
Video data is more cost-effective than motion capture data for learning 3D character motion controllers, yet synthesizing realistic and diverse behaviors directly from videos remains challenging. Previous approaches typically rely on…
Traditional 3D content creation tools empower users to bring their imagination to life by giving them direct control over a scene's geometry, appearance, motion, and camera path. Creating computer-generated videos, however, is a tedious…
With the availability of egocentric 3D hand-object interaction datasets, there is increasing interest in developing unified models for hand-object pose estimation and action recognition. However, existing methods still struggle to recognise…
Human behavior is fundamentally shaped by visual perception -- our ability to interact with the world depends on actively gathering relevant information and adapting our movements accordingly. Behaviors like searching for objects, reaching,…
Controlling both camera motion and object dynamics is essential for coherent and expressive video generation, yet current methods typically handle only one motion type or rely on ambiguous 2D cues that entangle camera-induced parallax with…
Recent advances in 3D scene reconstruction and 4D human animation have broadened adoption, but integrating the two remains difficult. Key challenges include placing humans at plausible locations and scales without interpenetration, aligning…
Scene-consistent video generation aims to create videos that explore 3D scenes based on a camera trajectory. Previous methods rely on video generation models with external memory for consistency, or iterative 3D reconstruction and…
Due to the problem of performance constraints of unsupervised video object detection, its large-scale application is limited. In response to this pain point, we propose another excellent method to solve this problematic point. By…
We extend multimodal transformers to include 3D camera motion as a conditioning signal for the task of video generation. Generative video models are becoming increasingly powerful, thus focusing research efforts on methods of controlling…
Recent work has shown that learned image compression strategies can outperform standard hand-crafted compression algorithms that have been developed over decades of intensive research on the rate-distortion trade-off. With growing…
Vision-centric autonomous driving has demonstrated excellent performance with economical sensors. As the fundamental step, 3D perception aims to infer 3D information from 2D images based on 3D-2D projection. This makes driving perception…
We present a novel video generation framework that integrates 3-dimensional geometry and dynamic awareness. To achieve this, we augment 2D videos with 3D point trajectories and align them in pixel space. The resulting 3D-aware video…
While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when users simultaneously specify text prompts, subject references,…
Modern visual generative models acquire rich visual knowledge through large-scale training, yet existing visual representations (such as pixels, latents, or tokens) remain external to the model and cannot directly exploit this knowledge for…
Despite tremendous recent progress, generative video models still struggle to capture real-world motion, dynamics, and physics. We show that this limitation arises from the conventional pixel reconstruction objective, which biases models…