Home Knowledge Base Novel View Synthesis

Novel View Synthesis

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis

arXiv:2606.01590v1 Announce Type: new Abstract: Modern vehicle platforms are equipped with a rich sensor suite, including LiDAR, calibrated multi-camera rigs, and accurate ego-motion, that in principle offers strong signal for re-rendering a driving scene from novel viewpoints. A growing line of recent work leverages video diffusion models for this task, using their generative priors to synthesize plausible novel views from sparse vehicle observations. In practice, however, existing methods...

arXiv CS 8d ago

DeblurNVS: Geometric Latent Diffusion for Novel View Synthesis from Sparse Motion-Blurred Images

Announce Type: new Abstract: Novel view synthesis (NVS) is a fundamental problem in computer vision and graphics. Recent advances in neural radiance fields (NeRF), 3D Gaussian Splatting (3DGS), and generative view synthesis have substantially improved its quality.

arXiv CS 8d ago

Fast and Lightweight Novel View Synthesis with Differentiable Multiplane Image

arXiv:2606.02068v1 Announce Type: new Abstract: Recently, novel view synthesis has witnessed remarkable progress, with mainstream methods such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) delivering impressive results. However, these approaches often struggle to balance rendering speed and model size, and their optimization-based training can be highly time-consuming. Furthermore, they typically rely on dense observations, often failing to produce satisfactory results...

arXiv CS 8d ago

RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video

new Abstract: Self-supervised novel view synthesis (NVS) remains challenging to scale, despite the abundance of video data, largely due to the brittleness of training on realistic videos and the hard-to-predict scaling behavior of multi-network system designs. We introduce RayDer, a unified, feed-forward transformer that consolidates camera estimation, scene reconstruction, and rendering into a single backbone, turning self-supervised NVS into a well-posed single-model scaling problem. A...

arXiv CS 9d ago

3DAE: Binaural Quality Assessment for Audio Novel View Synthesis with Spatial Maps and Benchmark

arXiv:2605.30469v1 Announce Type: new Abstract: 3D audio and novel-view acoustic synthesis models are usually evaluated with global metrics. However, global metrics often hide where and why binaural prediction fails. We propose a full-reference diagnostic framework that uses time-frequency audio error maps for magnitude, ILD, IPD, temporal alignment, loudness, and high-frequency failures, forming a 3D Audio Error Map (3DAE Map) for visual inspection.

arXiv CS 9d ago

LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis

arXiv:2603.20176v3 Announce Type: replace Abstract: Recent work has shown that neural networks can perform 3D tasks such as Novel View Synthesis (NVS) without explicit 3D reconstruction. Even so, we argue that strong 3D inductive biases are still helpful in the design of such networks.

arXiv CS 8d ago

DENSER: Depth-Guided Ensemble with Staged EFA-GS Reconstruction for Soccer Novel View Synthesis

arXiv:2606.01419v1 Announce Type: new Abstract: We propose DENSER, a Depth-guided ENSemble with Staged EFA-GS Reconstruction for soccer novel view synthesis. DENSER extends EFA-GS with three key contributions: (1) camera-height-based loss weighting that prioritises ground-level broadcast views, (2) monocular depth supervision from Depth-Anything-V2 to regularise geometry in textureless regions, and (3) a three-model pixel-average ensemble whose members diverge from a shared base checkpoint...

arXiv CS 8d ago

From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis

arXiv:2603.27455v2 Announce Type: replace Abstract: In this paper, we introduce NAS3R, a self-supervised feed-forward framework that jointly learns explicit 3D geometry and camera parameters with no ground-truth annotations and no pretrained priors. During training, NAS3R reconstructs 3D Gaussians from uncalibrated and unposed context views and renders target views using its self-predicted camera parameters, enabling self-supervised training from 2D photometric supervision. To ensure stable...

arXiv CS 7d ago

KC-3DGS: Kurtosis-Constrained Gaussian Splatting for High-Fidelity View Synthesis

arXiv:2606.03120v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) enables real-time novel view synthesis by representing scenes as collections of anisotropic Gaussians optimized via differentiable rasterization. However, standard pixel-space losses (L1, SSIM) constrain only aggregate reconstruction error, permitting the optimization to redistribute error across frequency scales. This leads to oversmoothing and structural artifacts, particularly in sparse-view settings where...

arXiv CS 7d ago

Equivariant Latent Alignment via Flow Matching under Group Symmetries

arXiv:2605.30705v2 Announce Type: replace Abstract: Geometry-aware generative models and novel view synthesis approaches have shown strong potential in visual fidelity and consistency. In parallel, equivariant representation learning has emerged as a powerful framework for constructing latent spaces where analytically known group transformations could act directly, capturing geometric structure in data and enhancing both interpretability and generalization in novel view synthesis. However,...

arXiv CS 6d ago