paper-with-me

홈 › Papers

Image Compression Using Novel View Synthesis Priors

2024-11-21 · Luyuan Peng, Mandar Chitre, Hari Vishnu, Yuen Min Too, Bharath Kalyan, Rajat Mishra, Soo Pieng Tan

Real-time visual feedback is essential for tetherless control of remotely operated vehicles, particularly during inspection and manipulation tasks. Though acoustic communication is the preferred choice for medium-range communication underwater, its limited bandwidth renders it impractical to transmit images or videos in real-time. To address this, we propose a model-based image compression technique that leverages prior mission information. Our approach employs trained machine-learning based novel view synthesis models, and uses gradient descent optimization to refine latent representations to help generate compressible differences between camera images and rendered images. We evaluate the proposed compression technique using a dataset from an artificial ocean basin, demonstrating superior compression ratios and image quality over existing techniques. Moreover, our method exhibits robustness to introduction of new objects within the scene, highlighting its potential for advancing tetherless remotely operated vehicle operations.

📄 PDF Abstract BibTeX arXiv:2411.13862

Code (0)

등록된 구현이 없습니다.

Tasks

Image CompressionNovel View Synthesis

Similar Papers 제목 키워드 기반

Sparse Input View Synthesis: 3D Representations and Reliable Priors

2024-11-20 · Nagabhushan Somraj

Novel view synthesis refers to the problem of synthesizing novel viewpoints of a scene given the images from a few viewpoints. This is a fundamental problem in computer vision and graphics, and enables a vast variety of …

Novel View SynthesisVideo CompressionVideo Stabilization

G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Images

2024-04-11 · CVPR 2024 1 · Zixiong Huang, Qi Chen, Libo Sun, Yifan Yang 외

Novel view synthesis aims to generate new view images of a given view image collection. Recent attempts address this problem relying on 3D geometry priors (e.g., shapes, sizes, and positions) learned from multi-view imag…

3D geometryNeRFNovel View Synthesis

OrbitNVS: Harnessing Video Diffusion Priors for Novel View Synthesis

2026-03-20 · Jinglin Liang, Zijian Zhou, Rui Huang, Shuangping Huang 외 arxiv

Novel View Synthesis (NVS) aims to generate unseen views of a 3D object given a limited number of known views. Existing methods often struggle to synthesize plausible views for unobserved regions, particularly under sing…

Novel View SynthesisVideo Generation

3D-LMVIC: Learning-based Multi-View Image Coding with 3D Gaussian Geometric Priors

2024-09-06 · Yujun Huang, Bin Chen, Niu Lian, Baoyi An 외

Existing multi-view image compression methods often rely on 2D projection-based similarities between views to estimate disparities. While effective for small disparities, such as those in stereo images, these methods str…

Autonomous DrivingDisparity EstimationImage Compression

Efficient Depth-Guided Urban View Synthesis

2024-07-17 · Sheng Miao, Jiaxin Huang, Dongfeng Bai, Weichao Qiu 외

Recent advances in implicit scene representation enable high-fidelity street view novel view synthesis. However, existing methods optimize a neural radiance field for each scene, relying heavily on dense training images …

Novel View Synthesis