# Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation

arXiv: https://arxiv.org/abs/2404.07933 · HTML: https://mlsanity.com/paper/2404.07933/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 47 of its 62 references that are in the map.
- First posted on arXiv 11 Apr 2024.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 47)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2112.00724/) (2021)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields](https://mlsanity.com/paper/2112.03907/) (2021)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.12251/) (2023)
- [GA-Net: Guided Aggregation Net for End-to-end Stereo Matching](https://mlsanity.com/paper/1904.06587/) (2019)
- [Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion](https://mlsanity.com/paper/2012.03762/) (2020)
- [GeoNeRF: Generalizing NeRF with Geometry Priors](https://mlsanity.com/paper/2111.13539/) (2021)
- [Neural Rays for Occlusion-aware Image-based Rendering](https://mlsanity.com/paper/2107.13421/) (2021)
- [LMSCNet: Lightweight Multiscale 3D Semantic Completion](https://mlsanity.com/paper/2008.10559/) (2020)
- [Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction](https://mlsanity.com/paper/1803.03893/) (2018)
- [Feature-metric Loss for Self-supervised Learning of Depth and Egomotion](https://mlsanity.com/paper/2007.10603/) (2020)
- [MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis](https://mlsanity.com/paper/2103.14910/) (2021)
- [Self-Supervised Monocular Depth Hints](https://mlsanity.com/paper/1909.09051/) (2019)
- [Anisotropic Convolutional Networks for 3D Semantic Scene Completion](https://mlsanity.com/paper/2004.02122/) (2020)
- [3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior](https://mlsanity.com/paper/2003.14052/) (2020)
- [HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2012.07356/) (2020)
- [S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds](https://mlsanity.com/paper/2012.09242/) (2020)
- [Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding](https://mlsanity.com/paper/1810.06125/) (2018)
- [StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction](https://mlsanity.com/paper/1807.08865/) (2018)
- [Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry](https://mlsanity.com/paper/1807.02570/) (2018)

## Built on by (most cited first, 6 of 6)

- [A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective](https://mlsanity.com/paper/2405.05173/) (2024)
- [Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion](https://mlsanity.com/paper/2507.06230/) (2025)
- [ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction](https://mlsanity.com/paper/2412.11210/) (2024)
- [IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals](https://mlsanity.com/paper/2506.20671/) (2025)
- [VOCA: Visual Odometry with Codec Awareness](https://mlsanity.com/paper/2607.00189/) (2026)
- [Rebenchmarking Unsupervised Monocular 3D Occupancy Prediction](https://mlsanity.com/paper/2602.06488/) (2026)

## Abstract (arXiv)

Inferring scene geometry from images via Structure from Motion is a long-standing and fundamental problem in computer vision. While classical approaches and, more recently, depth map predictions only focus on the visible parts of a scene, the task of scene completion aims to reason about geometry even in occluded regions. With the popularity of neural radiance fields (NeRFs), implicit representations also became popular for scene completion by predicting so-called density fields. Unlike explicit approaches. e.g. voxel-based methods, density fields also allow for accurate depth prediction and novel-view synthesis via image-based rendering. In this work, we propose to fuse the scene reconstruction from multiple images and distill this knowledge into a more accurate single-view scene reconstruction. To this end, we propose Multi-View Behind the Scenes (MVBTS) to fuse density fields from multiple posed images, trained fully self-supervised only from image data. Using knowledge distillation, we use MVBTS to train a single-view scene completion network via direct supervision called KDBTS. It achieves state-of-the-art performance on occupancy prediction, especially in occluded regions.