TRANSPR: Transparency Ray-Accumulating Neural 3D Scene Point Renderer

Kolos, Maria; Sevastopolsky, Artem; Lempitsky, Victor

doi:10.1109/3dv50981.2020.00127

Cited by 12 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural point cloud rendering has been studied in [KSL20; DZL∗20; AUL19]. These works mainly focus on rendering novel views from a single scene using a sparse set of input views.…”

Section: Related Workmentioning

confidence: 99%

Z2P: Instant Visualization of Point Clouds

Metzer

Hanocka

Giryes

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

We present a technique for visualizing point clouds using a neural network. Our technique allows for an instant preview of any point cloud, and bypasses the notoriously difficult surface reconstruction problem or the need to estimate oriented normals for splat‐based rendering. We cast the preview problem as a conditional image‐to‐image translation task, and design a neural network that translates point depth‐map directly into an image, where the point cloud is visualized as though a surface was reconstructed from it. Furthermore, the resulting appearance of the visualized point cloud can be, optionally, conditioned on simple control variables (e.g., color and light). We demonstrate that our technique instantly produces plausible images, and can, on‐the‐fly effectively handle noise, non‐uniform sampling, and thin surfaces sheets.

show abstract

“…Neural point cloud rendering has been studied in [KSL20; DZL∗20; AUL19]. These works mainly focus on rendering novel views from a single scene using a sparse set of input views.…”

Section: Related Workmentioning

confidence: 99%

Z2P: Instant Visualization of Point Clouds

Metzer

Hanocka

Giryes

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…NPBG [2] encodes the local geometric shapes and appearance by learning neural descriptors, which synthesizes high quality novel indoor views from point clouds. TRANSPR [13] extends NPBG by augmenting point descriptors with alpha values and replacing Z-buffer rasterization with ray marching, it is able to synthesize semi-transparent parts of the scene. ADOP [22] proposes a point-based differentiable neural rendering, where the parameters of all scenarios are optimized by designing the stages of the pipeline to be differentiable.…”

Section: Scene Synthesis By Neural Renderingmentioning

confidence: 99%

READ: Large-Scale Neural Scene Rendering for Autonomous Driving

Li¹,

Li²,

Ma³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…As with other point-based human models, the point cloud generated by POP can either be meshed using classical tools such as the Poisson Surface Reconstruction (PSR) [29], or directly rendered into realistic images using recent pointbased neural rendering techniques [2,30,50]. However, in this work, we do not rely on neural rendering to inpaint the gaps between the points.…”

Section: Training and Inferencementioning

confidence: 99%

The Power of Points for Modeling Humans in Clothing

Yang

Tang²,

Black

2021

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Unseen scan Fitted POP (point cloud)Animations with pose-dependent clothing deformation Figure 1: The Power of Points (POP) model for clothed humans. Based on a novel articulated dense point cloud representation, our cross-outfit model, named POP, produces pose-dependent shapes of clothed humans with coherent global shape and expressive local garment details. The trained model can be fitted to a single scan of an unseen subject wearing an unseen outfit, and can animate it with realistic pose-dependent clothing deformations. The results are color-coded with predicted point normals and rendered with a simple surfel-based renderer.

show abstract

TRANSPR: Transparency Ray-Accumulating Neural 3D Scene Point Renderer

Cited by 12 publications

References 12 publications

Z2P: Instant Visualization of Point Clouds

Z2P: Instant Visualization of Point Clouds

READ: Large-Scale Neural Scene Rendering for Autonomous Driving

The Power of Points for Modeling Humans in Clothing

Contact Info

Product

Resources

About