Papers › 3D Packing for Self-Supervised Monocular Depth Estimation

3D Packing for Self-Supervised Monocular Depth Estimation

6 May 2019CVPR 2020 6arXiv:1905.02693archive 2025-07-28

Vitor Guizilini, Rares Ambrus, Sudeep Pillai, Allan Raventos, Adrien Gaidon

Although cameras are ubiquitous, robotic platforms typically rely on active sensors like LiDAR for direct 3D perception. In this work, we propose a novel self-supervised monocular depth estimation method combining geometry with a new deep network, PackNet, learned only from unlabeled monocular videos. Our architecture leverages novel symmetrical packing and unpacking blocks to jointly learn to compress and decompress detail-preserving representations using 3D convolutions. Although self-supervised, our method outperforms other self, semi, and fully supervised methods on the KITTI benchmark. The 3D inductive bias in PackNet enables it to scale with input resolution and number of parameters without overfitting, generalizing better on out-of-domain data such as the NuScenes dataset. Furthermore, it does not require large-scale supervised pretraining on ImageNet and can run in real-time. Finally, we release DDAD (Dense Depth for Automated Driving), a new urban driving dataset with more challenging and accurate depth evaluation, thanks to longer-range and denser ground-truth depth generated from high-density LiDARs mounted on a fleet of self-driving cars operating world-wide.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

TRI-ML/DDAD officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
TRI-ML/packnet-sfm officialmentioned in papermentioned on GitHubpytorchMIT report
ToyotaResearchInstitute/packnet-sfm officialmentioned in paperMIT report
sejong-rcv/2021.Paper.TransDSSL mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Depth EstimationInductive BiasMonocular Depth EstimationSelf-Driving Cars

Datasets

Introduced by this paper, per the archive.

DDAD

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split PackNet-SfM absolute relative error 0.12 #68 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised PackNet-SfM M absolute relative error 0.107 #43 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Object Tracking Evaluation 2012 PackNet-SfM Abs Rel 0.071 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections