64 citations · 66 across the 14 of their papers we have counts for
21 papers
VARP: A Visual Adaptive Rearrangement Planner for Non-Monotone Object Rearrangement Planning
Hanwen Ren, Meng Zheng, Zhongpai Gao +4
Object rearrangement planning in cluttered environments is often non-monotone, requiring objects to be temporarily relocated before reaching their final destinations. Although sear…
STEP: Surgical Point Tracking from Sparse Endpoints and Pseudo-trajectories
Bing Fan, Anwesa Choudhuri, Zhongpai Gao +5
Surgical point tracking requires persistent correspondence through tissue deformation and occlusion, yet dense trajectory annotations are costly to obtain. We present STEP, a two-s…
Direct Conditional Parameterization for N-Dimensional Splatting
Zhongpai Gao, Benjamin Planche, Van Nguyen Nguyen +5
N-dimensional splatting extends 3D Gaussian Splatting with view direction and time to model view-dependent and dynamic effects. Each primitive is lifted into a joint distribution o…
FactorSplat: Appearance-Controllable Gaussian Proxies for Medical Volume Rendering
Zhongpai Gao, Benjamin Planche, Meng Zheng +3
Transfer functions (TFs) control color and visibility in medical volume rendering, but image-trained Gaussian proxies typically bake one transfer function into their appearance. We…
SCOPE-4D: Endoscopic 4D Geometry Foundation Models
Chaoyi Zhou, Zhongpai Gao, Anwesa Choudhuri +6
Geometric understanding supports endoscopic navigation and robotic assistance, but learning reliable endoscopic geometry faces two challenges: scarce geometric annotations and ambi…
XClipGS: Exact Half-Space Clipping for Medical Volume Gaussian Splatting
Zhongpai Gao, Benjamin Planche, Meng Zheng +4
Gaussian-splatting proxies enable interactive rendering of volumetric medical scans, but a clipping plane exposes anatomy not constrained by external-view training and intersects p…
Point Tracking in Surgery--The 2025 Surgical Tattoos in Infrared Challenge (STIRC2025)
Adam Schmidt, Mert Asim Karaoglu, Zijian Wu +32
Point tracking in surgery is crucial to enable applications in downstream tasks such as segmentation, 3D reconstruction, virtual tissue landmarking, autonomous probe-based scanning…
Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models
Meng Zheng, Samhita Marri, Anwesa Choudhuri +6
Vision-language-action (VLA) models provide a promising paradigm for scalable robotic manipulation, yet their reliance on success-only behavioral cloning leaves them brittle; lacki…
Consistent Instance Field for Dynamic Scene Understanding
Junyi Wu, Van Nguyen Nguyen, Benjamin Planche +11
We introduce Consistent Instance Field, a continuous and probabilistic spatio-temporal representation for dynamic scene understanding. Unlike prior methods that rely on discrete tr…
From Particles to Fields: Reframing Photon Mapping with Continuous Gaussian Photon Fields
Jiachen Tao, Benjamin Planche, Van Nguyen Nguyen +13
Accurately modeling light transport is essential for realistic image synthesis. Photon mapping provides physically grounded estimates of complex global illumination effects such as…
MedGRPO: Multi-Task Reinforcement Learning for Heterogeneous Medical Video Understanding
Yuhao Su, Anwesa Choudhuri, Zhongpai Gao +8
Large vision-language models struggle with medical video understanding, where spatial precision, temporal reasoning, and clinical semantics are critical. To address this, we first…
Universal Beta Splatting
Rong Liu, Zhongpai Gao, Benjamin Planche +8
We introduce Universal Beta Splatting (UBS), a unified framework that generalizes 3D Gaussian Splatting to N-dimensional anisotropic Beta kernels for explicit radiance field render…
Render-FM: Feedforward Model for Real-time Photorealistic Volumetric Rendering
Zhongpai Gao, Benjamin Planche, Meng Zheng +4
Photorealistic volumetric rendering of CT scans greatly benefits clinical workflows, yet neural approaches such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) re…
PolypSegTrack: Unified Foundation Model for Colonoscopy Video Analysis
Anwesa Choudhuri, Zhongpai Gao, Meng Zheng +3
Early detection, accurate segmentation, classification and tracking of polyps during colonoscopy are critical for preventing colorectal cancer. Many existing deep-learning-based me…
7DGS: Unified Spatial-Temporal-Angular Gaussian Splatting
Zhongpai Gao, Benjamin Planche, Meng Zheng +3
Real-time rendering of dynamic scenes with view-dependent effects remains a fundamental challenge in computer graphics. While recent advances in Gaussian Splatting have shown promi…
Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding
Andong Deng, Zhongpai Gao, Anwesa Choudhuri +6
Temporal awareness is essential for video large language models (LLMs) to understand and reason about events within long videos, enabling applications like dense video captioning a…
Order-aware Interactive Segmentation
Bin Wang, Anwesa Choudhuri, Meng Zheng +7
Interactive segmentation aims to accurately segment target objects with minimal user interactions. However, current methods often fail to accurately separate target objects from th…
3D Vision-Language Gaussian Splatting
Qucheng Peng, Benjamin Planche, Zhongpai Gao +5
Recent advancements in 3D reconstruction methods and vision-language models have propelled the development of multi-modal 3D scene understanding, which has vital applications in ro…
6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering
Zhongpai Gao, Benjamin Planche, Meng Zheng +3
Novel view synthesis has advanced significantly with the development of neural radiance fields (NeRF) and 3D Gaussian splatting (3DGS). However, achieving high quality without comp…
OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning
Anwesa Choudhuri, Girish Chowdhary, Alexander G. Schwing
We propose the new task 'open-world video instance segmentation and captioning'. It requires to detect, segment, track and describe with rich captions never before seen objects. Th…
Mask2Former for Video Instance Segmentation
Bowen Cheng, Anwesa Choudhuri, Ishan Misra +3
We find Mask2Former also achieves state-of-the-art performance on video instance segmentation without modifying the architecture, the loss or even the training pipeline. In this re…