Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

12-2025

Abstract

Depth estimation in dynamic, multi-object scenes remains a major challenge, especially under severe occlusions. Existing monocular models, including foundation models, struggle with instance-wise depth consistency due to their reliance on global regression. We tackle this problem from two key aspects: data and methodology. First, we introduce the Group Instance Depth (GID) dataset, the first large-scale video depth dataset with instance-level annotations, featuring 101,500 frames from real-world activity scenes. GID bridges the gap between synthetic and real-world depth data by providing high-fidelity depth supervision for multi-object interactions. Second, we propose InstanceDepth, the first occlusion-aware depth estimation framework for multi-object environments. Our twostage pipeline consists of (1) Holistic Depth Initialization, which assigns a coarse scene-level depth structure, and (2) Instance-Aware Depth Rectification, which refines instancewise depth using object masks, shape priors, and spatial relationships. By enforcing geometric consistency across occlusions, our method sets a new state-of-the-art on the GID dataset and multiple benchmarks. Our code and dataset can be found at https://github.com/ViktorLiang/ GID.

Discipline

Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the 2025 IEEE/CVF International Conference on Computer Vision (ICCV), Honolulu, Hawaii, October 19-23

First Page

7581

Last Page

7591

City or Country

USA

Download

Share

COinS