Publications

Papers, datasets, code, and project pages from 3DLG and collaborators.

Selected Publications

ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning
ICML 2026

ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning

Yiming Zhang, Jiacheng Chen, Jiaqi Tan, Yongsen Mao, Wenhu Chen, Angel X. Chang

Paper Website Code
VisACD: Visibility-Based GPU-Accelerated Approximate Convex Decomposition
Eurographics 2026 (Short Paper)

VisACD: Visibility-Based GPU-Accelerated Approximate Convex Decomposition

Egor Fokin, Manolis Savva

Paper Website Code
S2O: Static to Openable Enhancement for Articulated 3D Objects
WACV 2026

S2O: Static to Openable Enhancement for Articulated 3D Objects

Denys Iliash, Hanxiao Jiang, Yiming Zhang, Manolis Savva, Angel X. Chang

Paper Website Code
HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation
3DV 2026

HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation

Hou In Derek Pun, Hou In Ivan Tam, Austin T. Wang, Xiaoliang Huo, Angel X. Chang, Manolis Savva

Paper Website Code
SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesis
WACV 2026 (Oral)

SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesis

Hou In Ivan Tam, Hou In Derek Pun, Austin T. Wang, Angel X. Chang, Manolis Savva

Paper Website Code
SemLayoutDiff: Semantic Layout Generation with Diffusion Model for Indoor Scene Synthesis
3DV 2026

SemLayoutDiff: Semantic Layout Generation with Diffusion Model for Indoor Scene Synthesis

Xiaohao Sun, Divyam Goel, Angel X. Chang

Paper Website Code
iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videos
3DV 2026

iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videos

Weikun Peng, Jun Lv, Cewu Lu, Manolis Savva

Paper Website Code
NuiScene: Exploring Efficient Generation of Unbounded Outdoor Scenes
ICCV 2025

NuiScene: Exploring Efficient Generation of Unbounded Outdoor Scenes

Han-Hung Lee, Qinghong Han, Angel X. Chang

Paper Website Code
Diorama: Unleashing Zero-shot Single-view 3D Scene Modeling
ICCV 2025

Diorama: Unleashing Zero-shot Single-view 3D Scene Modeling

Qirui Wu, Denys Iliash, Daniel Ritchie, Manolis Savva, Angel X. Chang

Paper Website
ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding
ACL 2025

ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding

Austin T. Wang, ZeMing Gong, Angel X. Chang

Paper Website Code
SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects
ICLR 2025

SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects

Jiayi Liu, Denys Iliash, Angel X. Chang, Manolis Savva, Ali Mahdavi-Amiri

Paper Website Code
Duoduo CLIP: Efficient 3D Understanding with Multi-View Images
ICLR 2025

Duoduo CLIP: Efficient 3D Understanding with Multi-View Images

Han-Hung Lee, Yiming Zhang, Angel X. Chang

Paper Website Code
CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale
ICLR 2025, Workshop on Fine-Grained Visual Categorization at CVPR 2024

CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale

ZeMing Gong, Austin T. Wang, Joakim Bruslund Haurum, Scott C. Lowe, Graham W. Taylor, Angel X. Chang

Paper Website Code
An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion
3DV 2025

An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion

Xingguang Yan, Han-Hung Lee, Ziyu Wan, Angel X. Chang

Paper Website Code
SceneMotifCoder: Example-driven Visual Program Learning for Generating 3D Object Arrangements
3DV 2025 (Oral)

SceneMotifCoder: Example-driven Visual Program Learning for Generating 3D Object Arrangements

Hou In Ivan Tam, Hou In Derek Pun, Austin T. Wang, Angel X. Chang, Manolis Savva

Paper Website Video Code
CAGE: Controllable Articulation GEneration
CVPR 2024

CAGE: Controllable Articulation GEneration

Jiayi Liu, Hou In Ivan Tam, Ali Mahdavi-Amiri, Manolis Savva

Paper Website Video Code
Text-to-3D Shape Generation
State of the art report (STAR) at Eurographics 2024

Text-to-3D Shape Generation

Han-Hung Lee, Manolis Savva, Angel X. Chang

Paper Website
Generalizing Single-View 3D Shape Retrieval to Occlusions and Unseen Objects
3DV 2024

Generalizing Single-View 3D Shape Retrieval to Occlusions and Unseen Objects

Qirui Wu, Daniel Ritchie, Manolis Savva, Angel X. Chang

Paper Website Code
R3DS: Reality-linked 3D Scenes for Panoramic Scene Understanding
ECCV 2024, Workshop on Synthetic Data for Computer Vision - CVPR 2024

R3DS: Reality-linked 3D Scenes for Panoramic Scene Understanding

Qirui Wu, Sonia Raychaudhuri, Daniel Ritchie, Manolis Savva, Angel X. Chang

Paper Arxiv Website Video Code
TriCoLo: Trimodal Contrastive Loss for Text to Shape Retrieval
WACV 2024

TriCoLo: Trimodal Contrastive Loss for Text to Shape Retrieval

Yue Ruan*, Han-Hung Lee*, Yiming Zhang, Ke Zhang, Angel X. Chang

Paper Website Video Code
MOPA: Modular Object Navigation with PointGoal Agents
WACV 2024

MOPA: Modular Object Navigation with PointGoal Agents

Sonia Raychaudhuri, Tommaso Campari, Unnat Jain, Manolis Savva, Angel X. Chang

Paper Website Code
OPDMulti: Openable Part Detection for Multiple Objects
3DV 2024 (Oral)

OPDMulti: Openable Part Detection for Multiple Objects

Xiaohao Sun*, Hanxiao Jiang*, Manolis Savva, Angel X. Chang

Paper Website Code
Habitat Synthetic Scenes Dataset (HSSD): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation
CVPR 2024

Habitat Synthetic Scenes Dataset (HSSD): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation

Mukul Khanna*, Yongsen Mao*, Hanxiao Jiang, Sanjay Haresh, Brennan Shacklett, Dhruv Batra, Alexander Clegg, Eric Undersander, Angel X. Chang, Manolis Savva

Paper Website Code
A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset
NeurIPS datasets and benchmarks, 2023

A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset

Zahra Gharaee*, ZeMing Gong*, Nicholas Pellegrino*, Iuliia Zarubiieva, Joakim Bruslund Haurum, Scott C. Lowe, Jaclyn T.A. McKeown, Chris C.Y. Ho, Joschka McLeod, Yi-Yun C Wei, Jireh Agda, Sujeevan Ratnasingham, Dirk Steinke, Angel X. Chang, Graham W. Taylor, Paul Fieguth

Paper Website Code
3DSSR: 3D Subscene Retrieval
Workshop on Structural and Compositional Learning on 3D Data - CVPR 2023

3DSSR: 3D Subscene Retrieval

Reza Asad, Manolis Savva

Paper Website Video Code
Multi3DRefer: Grounding Text Description to Multiple 3D Objects
ICCV 2023

Multi3DRefer: Grounding Text Description to Multiple 3D Objects

Yiming Zhang, Zeming Gong, Angel X. Chang

Paper Website Code
PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects
ICCV 2023

PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects

Jiayi Liu, Ali Mahdavi-Amiri, Manolis Savva

Paper Website Video Code
UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding
ICCV 2023

UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding

Dave Zhenyu Chen, Ronghang Hu, Xinlei Chen, Matthias Nießner, Angel X. Chang

Paper Website
Exploiting Proximity-Aware Tasks for Embodied Social Navigation
ICCV 2023

Exploiting Proximity-Aware Tasks for Embodied Social Navigation

Enrico Cancelli, Tommaso Campari, Luciano Serafini, Angel X. Chang, Lamberto Ballan

Paper Code
HomeRobot: Open Vocabulary Mobile Manipulation
CoRL 2023

HomeRobot: Open Vocabulary Mobile Manipulation

Sriram Yenamandra, Arun Ramachandran, Karmesh Yadav, Austin Wang, Mukul Khanna, Theo Gervet, Jimmy (Tsung-Yen) Yang, Vidhi Jain, Alexander Clegg, John Turner, Zsolt Kira, Manolis Savva, Angel X. Chang, Devendra Chaplot, Dhruv Batra, Roozbeh Mottaghi, Yonatan Bisk, Chris Paxton

Paper Website Video Code
Advances in Data-Driven Analysis and Synthesis of 3D Indoor Scenes
Computer Graphics Forum 2023 STAR (State of the Art Report)

Advances in Data-Driven Analysis and Synthesis of 3D Indoor Scenes

Akshay Gadi Patil, Supriya Gadi Patil, Manyi Li, Matthew Fisher, Manolis Savva, Hao Zhang

Paper
Habitat-Matterport 3D Semantics Dataset
CVPR 2023

Habitat-Matterport 3D Semantics Dataset

Karmesh Yadav, Ram Ramrakhya, Santhosh Kumar Ramakrishnan, Theo Gervet, John Turner, Aaron Gokaslan, Noah Maestre, Angel X. Chang, Dhruv Batra, Manolis Savva, Alexander Clegg, Devendra Chaplot

Paper Website Code
Evaluating 3D Shape Analysis Methods for Robustness to Rotation Invariance
CRV 2023

Evaluating 3D Shape Analysis Methods for Robustness to Rotation Invariance

Supriya Gadi Patil, Angel X. Chang, Manolis Savva

Paper Website Code
Emergence of Maps in the Memories of Blind Navigation Agents
Outstanding Paper Award - ICLR 2023

Emergence of Maps in the Memories of Blind Navigation Agents

Erik Wijmans, Manolis Savva, Irfan Essa, Stefan Lee, Ari Morcos, Dhruv Batra

Paper Website Code
Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments
EMNLP 2021

Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments

Sonia Raychaudhuri, Saim Wani, Shivansh Patel, Unnat Jain, Angel X. Chang

Paper Website Code
Plan2Scene: Converting Floorplans to 3D Scenes
CVPR 2021

Plan2Scene: Converting Floorplans to 3D Scenes

Madhawa Vidanapathirana, Qirui Wu, Yasutaka Furukawa, Angel X. Chang, Manolis Savva

Paper Website Code