Searcharxiv⌕ Search

arXiv subjects

Chenfanfu Jiang

Publications and source records attributed to Chenfanfu Jiang.

95 records · Page 6Linked to original sources

Fast and Scalable Position-Based Layout Synthesis

The arrangement of objects into a layout can be challenging for non-experts, as is affirmed by the existence of interior design professionals. Recent research into the automation of this task has yielded methods that can synthesize layouts of objects respecting aesthetic and functional constraints that are non-linear and competing. These methods usually adopt a stochastic optimization scheme, which samples from different layout configurations, a process that is slow and inefficient. We introduce an physics-motivated, continuous layout synthesis technique, which results in a significant gain in speed and is readily scalable. We demonstrate our method on a variety of examples and show that it achieves results similar to conventional layout synthesis based on Markov chain Monte Carlo (McMC) state-search, but is faster by at least an order of magnitude and can handle layouts of unprecedented size as well as tightly-packed layouts that can overwhelm McMC.

cs.GR↗

Human-centric Indoor Scene Synthesis Using Stochastic Grammar

We present a human-centric method to sample and synthesize 3D room layouts and 2D images thereof, to obtain large-scale 2D/3D image data with perfect per-pixel ground truth. An attributed spatial And-Or graph (S-AOG) is proposed to represent indoor scenes. The S-AOG is a probabilistic grammar model, in which the terminal nodes are object entities. Human contexts as contextual relations are encoded by Markov Random Fields (MRF) on the terminal nodes. We learn the distributions from an indoor scene dataset and sample new layouts using Monte Carlo Markov Chain. Experiments demonstrate that our method can robustly sample a large variety of realistic room layouts based on three criteria: (i) visual realism comparing to a state-of-the-art room arrangement method, (ii) accuracy of the affordance maps with respect to groundtruth, and (ii) the functionality and naturalness of synthesized rooms evaluated by human subjects. The code is available at https://github.com/SiyuanQi/human-centric-scene-synthesis.

cs.CV↗

Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars

We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of training, benchmarking, and diagnosing learning-based computer vision and robotics algorithms. In particular, we devise a learning-based pipeline of algorithms capable of automatically generating and rendering a potentially infinite variety of indoor scenes by using a stochastic grammar, represented as an attributed Spatial And-Or Graph, in conjunction with state-of-the-art physics-based rendering. Our pipeline is capable of synthesizing scene layouts with high diversity, and it is configurable inasmuch as it enables the precise customization and control of important attributes of the generated scenes. It renders photorealistic RGB images of the generated scenes while automatically synthesizing detailed, per-pixel ground truth data, including visible surface depth and normal, object identity, and material information (detailed to object parts), as well as environments (e.g., illuminations and camera viewpoints). We demonstrate the value of our synthesized dataset, by improving performance in certain machine-learning-based scene understanding tasks--depth and surface normal prediction, semantic segmentation, reconstruction, etc.--and by providing benchmarks for and diagnostics of trained models by modifying object attributes and scene properties in a controllable manner.

cs.CV↗

Position-Based Multi-Agent Dynamics for Real-Time Crowd Simulation (MiG paper)

Exploiting the efficiency and stability of Position-Based Dynamics (PBD), we introduce a novel crowd simulation method that runs at interactive rates for hundreds of thousands of agents. Our method enables the detailed modeling of per-agent behavior in a Lagrangian formulation. We model short-range and long-range collision avoidance to simulate both sparse and dense crowds. On the particles representing agents, we formulate a set of positional constraints that can be readily integrated into a standard PBD solver. We augment the tentative particle motions with planning velocities to determine the preferred velocities of agents, and project the positions onto the constraint manifold to eliminate colliding configurations. The local short-range interaction is represented with collision and frictional contact between agents, as in the discrete simulation of granular materials. We incorporate a cohesion model for modeling collective behaviors and propose a new constraint for dealing with potential future collisions. Our new method is suitable for use in interactive games.

cs.GR↗

An angular momentum conserving Affine-Particle-In-Cell method

We present a new technique for transferring momentum and velocity between particles and grid with Particle-In-Cell (PIC) calculations which we call Affine-Particle-In-Cell (APIC). APIC represents particle velocities as locally affine, rather than locally constant as in traditional PIC. We show that this representation allows APIC to conserve linear and angular momentum across transfers while also dramatically reducing numerical diffusion usually associated with PIC. Notably, conservation is achieved with lumped mass, as opposed to the more commonly used Fluid Implicit Particle (FLIP) transfers which require a 'full' mass matrix for exact conservation. Furthermore, unlike FLIP, APIC retains a filtering property of the original PIC and thus does not accumulate velocity modes on particles as FLIP does. In particular, we demonstrate that APIC does not experience velocity instabilities that are characteristic of FLIP in a number of Material Point Method (MPM) hyperelasticity calculations. Lastly, we demonstrate that when combined with the midpoint rule for implicit update of grid momentum that linear and angular momentum are exactly conserved.

physics.comp-ph↗