A Unified 3D Object Perception Framework for Real-Time Outside-In Multi-Camera Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yizhou, Pusegaonkar, Sameer, Wang, Yuxing, Li, Anqi, Kumar, Vishal, Sethi, Chetan, Aiyer, Ganapathy, He, Yun, Thakkar, Kartikay, Rathi, Swapnil, Rupde, Bhushan, Tang, Zheng, Biswas, Sujit
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911378800902144
author Wang, Yizhou
Pusegaonkar, Sameer
Wang, Yuxing
Li, Anqi
Kumar, Vishal
Sethi, Chetan
Aiyer, Ganapathy
He, Yun
Thakkar, Kartikay
Rathi, Swapnil
Rupde, Bhushan
Tang, Zheng
Biswas, Sujit
author_facet Wang, Yizhou
Pusegaonkar, Sameer
Wang, Yuxing
Li, Anqi
Kumar, Vishal
Sethi, Chetan
Aiyer, Ganapathy
He, Yun
Thakkar, Kartikay
Rathi, Swapnil
Rupde, Bhushan
Tang, Zheng
Biswas, Sujit
contents Accurate 3D object perception and multi-target multi-camera (MTMC) tracking are fundamental for the digital transformation of industrial infrastructure. However, transitioning "inside-out" autonomous driving models to "outside-in" static camera networks presents significant challenges due to heterogeneous camera placements and extreme occlusion. In this paper, we present an adapted Sparse4D framework specifically optimized for large-scale infrastructure environments. Our system leverages absolute world-coordinate geometric priors and introduces an occlusion-aware ReID embedding module to maintain identity stability across distributed sensor networks. To bridge the Sim2Real domain gap without manual labeling, we employ a generative data augmentation strategy using the NVIDIA COSMOS framework, creating diverse environmental styles that enhance the model's appearance-invariance. Evaluated on the AI City Challenge 2025 benchmark, our camera-only framework achieves a state-of-the-art HOTA of $45.22$. Furthermore, we address real-time deployment constraints by developing an optimized TensorRT plugin for Multi-Scale Deformable Aggregation (MSDA). Our hardware-accelerated implementation achieves a $2.15\times$ speedup on modern GPU architectures, enabling a single Blackwell-class GPU to support over 64 concurrent camera streams.
format Preprint
id arxiv_https___arxiv_org_abs_2601_10819
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Unified 3D Object Perception Framework for Real-Time Outside-In Multi-Camera Systems
Wang, Yizhou
Pusegaonkar, Sameer
Wang, Yuxing
Li, Anqi
Kumar, Vishal
Sethi, Chetan
Aiyer, Ganapathy
He, Yun
Thakkar, Kartikay
Rathi, Swapnil
Rupde, Bhushan
Tang, Zheng
Biswas, Sujit
Computer Vision and Pattern Recognition
Accurate 3D object perception and multi-target multi-camera (MTMC) tracking are fundamental for the digital transformation of industrial infrastructure. However, transitioning "inside-out" autonomous driving models to "outside-in" static camera networks presents significant challenges due to heterogeneous camera placements and extreme occlusion. In this paper, we present an adapted Sparse4D framework specifically optimized for large-scale infrastructure environments. Our system leverages absolute world-coordinate geometric priors and introduces an occlusion-aware ReID embedding module to maintain identity stability across distributed sensor networks. To bridge the Sim2Real domain gap without manual labeling, we employ a generative data augmentation strategy using the NVIDIA COSMOS framework, creating diverse environmental styles that enhance the model's appearance-invariance. Evaluated on the AI City Challenge 2025 benchmark, our camera-only framework achieves a state-of-the-art HOTA of $45.22$. Furthermore, we address real-time deployment constraints by developing an optimized TensorRT plugin for Multi-Scale Deformable Aggregation (MSDA). Our hardware-accelerated implementation achieves a $2.15\times$ speedup on modern GPU architectures, enabling a single Blackwell-class GPU to support over 64 concurrent camera streams.
title A Unified 3D Object Perception Framework for Real-Time Outside-In Multi-Camera Systems
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.10819