Publication
Self-Supervised Surround-View Depth Estimation with Volumetric Feature Fusion
2022.11.08

36th annual Conference on Neural Information Processing Systems (NeurIPS 2022)에 실린 김중희, 허준화, Tien Nguyen, 정성균 저자의 “Self-supervised surround-view depth estimation with volumetric feature fusion” 논문을 소개합니다. NeurIPS는 세계적인 머신러닝(ML)·AI 학회로 가장 최신의 머신러닝 리서치 기술에 대해 학계와 산업계를 포함한 다양한 연구자들이 참여하여 소개하고 있습니다.


Conference


https://openreview.net/forum?id=0PfIQs-ttQQ

https://github.com/42dot/VFDepth


Publication


  • Title: Self-supervised surround-view depth estimation with volumetric feature fusion
  • Authors: Jung-Hee Kim, Junhwa Hur, Tien Nguyen, Seong-Gyun Jeong
  • Abstract: We present a self-supervised depth estimation approach using a unified volumetric feature fusion for surround-view images. Given a set of surround-view images, our method constructs a volumetric feature map by extracting image feature maps from surround-view images and fuse the feature maps into a shared, unified 3D voxel space. The volumetric feature map then can be used for estimating a depth map at each surround view by projecting it into an image coordinate. A volumetric feature contains 3D information at its local voxel coordinate; thus our method can also synthesize a depth map at arbitrary rotated viewpoints by projecting the volumetric feature map into the target viewpoints. Furthermore, assuming static camera extrinsics in the multi-camera system, we propose to estimate a canonical camera motion from the volumetric feature map. Our method leverages 3D spatio- temporal context to learn metric-scale depth and the canonical camera motion in a self-supervised manner. Our method outperforms the prior arts on DDAD and nuScenes datasets, especially estimating more accurate metric-scale depth and consistent depth between neighboring views.


Jung-Hee Kim | AD Algorithm



I’m in charge of developing 3D vision models for autonomous vehicles.

Active Learning을 통한 지속적인 모델 성능 개선
Tech
2024.11.14
42dot LLM 1.3B
Tech
2024.11.14
42dot at CES 2024: Software-Defined Vehicle Technology
Tech
2024.11.14
영지식 증명과 블록체인 그리고 SDV, 모빌리티
Tech
2024.11.14
Team 42dot Wins 2nd Place in the Autonomous Driving Challenge at CVPR 2023
Tech
2024.11.14
Joint Unsupervised and Supervised Learning for Context-aware Language Identification
Publication
2024.11.14
AWS IoT Core Resource Deployment via CDK
Tech
2024.11.14
ML Data Platform for Continuous Learning
Tech
2024.11.14
속도와 보안이 강화된 OTA 업데이트
Tech
2024.11.14
Foros : 자동차에 합의 알고리즘을?
Tech
2024.11.14
42dot MCMOT(Multi-Camera Multi-Object Tracking) 챌린지
Tech
2024.11.14
42dot이 그리는 미래 모빌리티 세상
Insight
2024.11.14