49 citations · 59 across the 19 of their papers we have counts for
9 papers · 1 filter
GATOR: Generative and Agentic 3D Object Reconstruction From Casual Images
Qirui Wu, Stan Birchfield, Hesam Rabeti +2
Reconstructing complete, scene-aligned 3D objects from casual images requires integrating sparse, uncertain observations and inferring surfaces hidden by occlusions. We present GAT…
MG-VQA: Manipulation Grounded Visual Question Answering with VLMs
Vineet Bhat, Siyi Chen, Mikaela Angelina Uy +6
Vision-language models (VLMs) have shown promising spatial reasoning capabilities from static visual inputs, where the evidence needed to answer a question is available in the prov…
CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction
Xianghui Xie, Bowen Wen, Yan Chang +5
Accurate capture of human-object interaction from ubiquitous sensors like RGB cameras is important for applications in human understanding, gaming, and robot learning. However, inf…
SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL
Siyi Chen, Mikaela Angelina Uy, Chan Hee Song +6
Vision Language Models (VLMs) demonstrate strong qualitative visual understanding, but struggle with metrically precise spatial reasoning required for embodied applications. The ag…
BOP-ASK: Object-Interaction Reasoning for Vision-Language Models
Vineet Bhat, Sungsu Kim, Valts Blukis +6
Vision Language Models (VLMs) have achieved impressive performance on spatial reasoning benchmarks, yet these evaluations mask critical weaknesses in understanding object interacti…
BOP Challenge 2024 on Model-Based and Model-Free 6D Object Pose Estimation
Van Nguyen Nguyen, Stephen Tyree, Andrew Guo +16
We present the evaluation methodology, datasets and results of the BOP Challenge 2024, the 6th in a series of public competitions organized to capture the state of the art in 6D ob…
RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics
Chan Hee Song, Valts Blukis, Jonathan Tremblay +3
Spatial understanding is a crucial capability that enables robots to perceive their surroundings, reason about their environment, and interact with it meaningfully. In modern robot…
NeRFDeformer: NeRF Transformation from a Single View via 3D Scene Flows
Zhenggang Tang, Zhongzheng Ren, Xiaoming Zhao +4
We present a method for automatically modifying a NeRF representation based on a single observation of a non-rigid transformed version of the original scene. Our method defines the…
FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
Bowen Wen, Wei Yang, Jan Kautz +1
We present FoundationPose, a unified foundation model for 6D object pose estimation and tracking, supporting both model-based and model-free setups. Our approach can be instantly a…