mlsanityData to 7 Oct 2026

SVDM: Single-View Diffusion Model for Pseudo-Stereo 3D Object Detection

arXiv 2307.02270 ↗First posted 5 Jul 2023cs.CV cs.AIcited by 0

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

One of the key problems in 3D object detection is to reduce the accuracy gap between methods based on LiDAR sensors and those based on monocular cameras. A recently proposed framework for monocular 3D detection based on Pseudo-Stereo has received considerable attention in the community. However, so far these two problems are discovered in existing practices, including (1) monocular depth estimation and Pseudo-Stereo detector must be trained separately, (2) Difficult to be compatible with different stereo detectors and (3) the overall calculation is large, which affects the reasoning speed. In this work, we propose an end-to-end, efficient pseudo-stereo 3D detection framework by introducing a Single-View Diffusion Model (SVDM) that uses a few iterations to gradually deliver right informative pixels to the left image. SVDM allows the entire pseudo-stereo 3D detection pipeline to be trained end-to-end and can benefit from the training of stereo detectors. Afterwards, we further explore the application of SVDM in depth-free stereo 3D detection, and the final framework is compatible with most stereo detectors. Among multiple benchmarks on the KITTI dataset, we achieve new state-of-the-art performance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 78 of its 91 references that are in the map. First posted on arXiv 5 Jul 2023.

Builds on

78 of 91 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022DiffusionDet: Diffusion Model for Object Detection17 Nov
  2. 2022BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models16 May

Other references · 76

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2022Scalable Diffusion Models with Transformerscited by 5,931
  9. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  10. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  11. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  12. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
38 more
  1. 2022A ConvNet for the 2020scited by 3,545
  2. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  3. 2023Consistency Modelscited by 1,778
  4. 2017Decoupled Weight Decay Regularizationcited by 1,722
  5. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  6. 2019Objects as Pointscited by 1,172
  7. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  8. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  9. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  10. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 773
  11. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  12. 2021Vector-quantized Image Modeling with Improved VQGANcited by 656
  13. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  14. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  15. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  16. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 326
  17. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 279
  18. 20163D Bounding Box Estimation Using Deep Learning and Geometrycited by 277
  19. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  20. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 251
  21. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 221
  22. 2019Disentangling Monocular 3D Object Detectioncited by 215
  23. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 206
  24. 2020SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimationcited by 202
  25. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
  26. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 184
  27. 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
  28. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
  29. 2019Stereo R-CNN based 3D Object Detection for Autonomous Drivingcited by 163
  30. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 155
  31. 2020MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationshipscited by 153
  32. 2020RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Drivingcited by 150
  33. 2020Feature-metric Loss for Self-supervised Learning of Depth and Egomotioncited by 140
  34. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 138
  35. 2019Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Drivingcited by 137
  36. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  37. 2020Kinematic 3D Object Detection in Monocular Videocited by 116
  38. 2020Rethinking Pseudo-LiDAR Representationcited by 109

50 most cited of 76 All 76 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 20233DifFusionDet: Diffusion Model for 3D Object Detection with Robust LiDAR-Camera Fusion
  2. 20233DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features
  3. 2024DiffuBox: Refining 3D Object Detection with Point Diffusion
  4. 2024FSMDet: Vision-guided feature diffusion for fully sparse 3D detector
  5. 2023DiffRef3D: A Diffusion-based Proposal Refinement Framework for 3D Object Detection
  6. 2022MSF3DDETR: Multi-Sensor Fusion 3D Detection Transformer for Autonomous Driving
  7. 2025Perspective-Invariant 3D Object Detection
  8. 2023DiffuVolume: Diffusion Model for Volume based Stereo Matching