paper-with-me

Papers

RendBEV: Semantic Novel View Synthesis for Self-Supervised Bird's Eye View Segmentation

2025-02-20 · Henrique Piñeiro Monteagudo, Leonardo Taccari, Aurel Pjetri, Francesco Sambo, Samuele Salti

Bird's Eye View (BEV) semantic maps have recently garnered a lot of attention as a useful representation of the environment to tackle assisted and autonomous driving tasks. However, most of the existing work focuses on the fully supervised setting, training networks on large annotated datasets. In this work, we present RendBEV, a new method for the self-supervised training of BEV semantic segmentation networks, leveraging differentiable volumetric rendering to receive supervision from semantic perspective views computed by a 2D semantic segmentation model. Our method enables zero-shot BEV semantic segmentation, and already delivers competitive results in this challenging setting. When used as pretraining to then fine-tune on labeled BEV ground-truth, our method significantly boosts performance in low-annotation regimes, and sets a new state of the art when fine-tuning on all available labels.

📄 PDF Abstract BibTeX arXiv:2502.14792

Code (0)

등록된 구현이 없습니다.

Tasks

2D Semantic SegmentationAutonomous DrivingNovel View SynthesisSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation

2021-04-12 · Hongbin Xu, Zhipeng Zhou, Yu Qiao, Wenxiong Kang 외

Recent studies have witnessed that self-supervised methods based on view synthesis obtain clear progress on multi-view stereo (MVS). However, existing methods rely on the assumption that the corresponding points among di…

Data Augmentation

Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization

2022-11-28 · Stefan Stojanov, Anh Thai, Zixuan Huang, James M. Rehg

A hallmark of the deep learning era for computer vision is the successful use of large-scale labeled datasets to train feature representations for tasks ranging from object recognition and semantic segmentation to optica…

Novel View SynthesisObjectObject RecognitionOptical Flow Estimation+2

SODA: Bottleneck Diffusion Models for Representation Learning

2023-11-29 · CVPR 2024 1 · Drew A. Hudson, Daniel Zoran, Mateusz Malinowski, Andrew K. Lampinen 외

We introduce SODA, a self-supervised diffusion model, designed for representation learning. The model incorporates an image encoder, which distills a source view into a compact representation, that, in turn, guides the g…

DecoderDenoisingImage GenerationLinear-Probe Classification+2

SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction

2023-11-21 · CVPR 2024 1 · Yuanhui Huang, Wenzhao Zheng, Borui Zhang, Jie zhou 외

3D occupancy prediction is an important task for the robustness of vision-centric autonomous driving, which aims to predict whether each point is occupied in the surrounding 3D space. Existing methods usually require 3D …

Autonomous DrivingDepth EstimationMonocular Depth EstimationPrediction

Self-supervised Light Field View Synthesis Using Cycle Consistency

2020-08-12 · Yang Chen, Martin Alain, Aljosa Smolic

High angular resolution is advantageous for practical applications of light fields. In order to enhance the angular resolution of light fields, view synthesis methods can be utilized to generate dense intermediate views …