Related papers: VistaBot: View-Robust Robot Manipulation via Spati…
We present SynShot, a novel method for the few-shot inversion of a drivable head avatar based on a synthetic prior. We tackle three major challenges. First, training a controllable 3D generative network requires a large number of diverse…
Goal-oriented planning, or anticipating a series of actions that transition an agent from its current state to a predefined objective, is crucial for developing intelligent assistants aiding users in daily procedural tasks. The problem…
Video generation models have advanced rapidly and are beginning to show a strong understanding of physical dynamics. In this paper, we investigate how far an advanced video generation model such as Veo-3 can support generalizable robotic…
Visual recognition models are not invariant to viewpoint changes in the 3D world, as different viewing directions can dramatically affect the predictions given the same object. Although many efforts have been devoted to making neural…
Recent unified 3D generation models have made remarkable progress in producing high-quality 3D assets from a single image. Notably, layout-aware approaches such as SAM3D can reconstruct multiple objects while preserving their spatial…
This work introduces VISY-REVE: a novel pipeline to validate image processing algorithms for Vision-Based Navigation. Traditional validation methods such as synthetic rendering or robotic testbed acquisition suffer from difficult setup and…
3D Visual Grounding (3DVG) seeks to locate target objects in 3D scenes using natural language descriptions, enabling downstream applications such as augmented reality and robotics. Existing approaches typically rely on labeled 3D data and…
Large image diffusion models enable novel view synthesis with high quality and excellent zero-shot capability. However, such models based on image-to-image translation have no guarantee of view consistency, limiting the performance for…
Video Diffusion Models (VDMs) have emerged as powerful generative tools, capable of synthesizing high-quality spatiotemporal content. Yet, their potential goes far beyond mere video generation. We argue that the training dynamics of VDMs,…
Surround-view perception is increasingly important for robotic navigation and loco-manipulation, especially in human-in-the-loop settings such as teleoperation, data collection, and emergency takeover. However, current robotic visual…
We present See360, which is a versatile and efficient framework for 360 panoramic view interpolation using latent space viewpoint estimation. Most of the existing view rendering approaches only focus on indoor or synthetic 3D environments…
Visual representations play a crucial role in developing generalist robotic policies. Previous vision encoders, typically pre-trained with single-image reconstruction or two-image contrastive learning, tend to capture static information,…
Vision-Language-Action (VLA) models have recently achieved remarkable progress in robotic perception and control, yet most existing approaches primarily rely on VLM trained using 2D images, which limits their spatial understanding and…
Existing reconstruction-based novel view synthesis methods for driving scenes focus on synthesizing camera views along the recorded trajectory of the ego vehicle. Their image rendering performance will severely degrade on viewpoints falling…
We propose Camera Splatting, a novel view optimization framework for novel view synthesis. Each camera is modeled as a 3D Gaussian, referred to as a camera splat, and virtual cameras, termed point cameras, are placed at 3D points sampled…
4D radar has received significant attention in autonomous driving thanks to its robustness under adverse weathers. Due to the sparse points and noisy measurements of the 4D radar, most of the research finish the 3D object detection task by…
Recent volumetric 3D reconstruction methods can produce very accurate results, with plausible geometry even for unobserved surfaces. However, they face an undesirable trade-off when it comes to multi-view fusion. They can fuse all available…
Since vision-based manipulation policies are typically trained from data gathered from a single viewpoint, their performance drops when the view changes during deployment. Naively aggregating demonstrations from numerous random views is not…
Visuotactile sensing offers rich contact information that can help mitigate performance bottlenecks in imitation learning, particularly under vision-limited conditions, such as ambiguous visual cues or occlusions. Effectively fusing visual…
Understanding and manipulating articulated objects, such as doors and drawers, is crucial for robots operating in human environments. We wish to develop a system that can learn to articulate novel objects with no prior interaction, after…