Rui Wang

Jingsen Zhu, Fujun Luan, Yuchi Huo et al.

Indoor scenes typically exhibit complex, spatially-varying appearance from global illumination, making inverse rendering a challenging ill-posed problem. This work presents an end-to-end, learning-based inverse rendering framework incorporating differentiable Monte Carlo raytracing with importance sampling. The framework takes a single image as input to jointly recover the underlying geometry, spatially-varying lighting, and photorealistic materials. Specifically, we introduce a physically-based differentiable rendering layer with screen-space ray tracing, resulting in more realistic specular reflections that match the input photo. In addition, we create a large-scale, photorealistic indoor scene dataset with significantly richer details like complex furniture and dedicated decorations. Further, we design a novel out-of-view lighting network with uncertainty-aware refinement leveraging hypernetwork-based neural radiance fields to predict lighting outside the view of the input photo. Through extensive evaluations on common benchmark datasets, we demonstrate superior inverse rendering quality of our method compared to state-of-the-art baselines, enabling various applications such as complex object insertion and material editing with high fidelity. Code and data will be made available at \url{https://jingsenzhu.github.io/invrend}.

Jingsen Zhu, Yuchi Huo, Qi Ye et al.

In this work, we present I$^2$-SDF, a new method for intrinsic indoor scene reconstruction and editing using differentiable Monte Carlo raytracing on neural signed distance fields (SDFs). Our holistic neural SDF-based framework jointly recovers the underlying shapes, incident radiance and materials from multi-view images. We introduce a novel bubble loss for fine-grained small objects and error-guided adaptive sampling scheme to largely improve the reconstruction quality on large-scale indoor scenes. Further, we propose to decompose the neural radiance field into spatially-varying material of the scene as a neural field through surface-based, differentiable Monte Carlo raytracing and emitter semantic segmentations, which enables physically based and photorealistic scene relighting and editing applications. Through a number of qualitative and quantitative experiments, we demonstrate the superior quality of our method on indoor scene reconstruction, novel view synthesis, and scene editing compared to state-of-the-art baselines.

Maxime Oquab, Daniel Haziza, Ludovic Schwartz et al.

As the quality of few shot facial animation from landmarks increases, new applications become possible, such as ultra low bandwidth video chat compression with a high degree of realism. However, there are some important challenges to tackle in order to improve the experience in real world conditions. In particular, the current approaches fail to represent profile views without distortions, while running in a low compute regime. We focus on this key problem by introducing a multi-frames embedding dubbed Frontalizer to improve profile views rendering. In addition to this core improvement, we explore the learning of a latent code conditioning generations along with landmarks to better convey facial expressions. Our dense models achieves 22% of improvement in perceptual quality and 73% reduction of landmark error over the first order model baseline on a subset of DFDC videos containing head movements. Declined with mobile architectures, our models outperform the previous state-of-the-art (improving perceptual quality by more than 16% and reducing landmark error by more than 47% on two datasets) while running on real time on iPhone 8 with very low bandwidth requirements.

Zhi He, Rui Wang, Wei Hua et al.

This paper propose a interactive 3D modeling method and corresponding system based on single or multiple uncalibrated images. The main feature of this method is that, according to the modeling habits of ordinary people, the 3D model of the target is reconstructed from coarse to fine images. On the basis of determining the approximate shape, the user adds or modify projection constraints and spatial constraints, and apply topology modification, gradually realize camera calibration, refine rough model, and finally complete the reconstruction of objects with arbitrary geometry and topology. During the interactive process, the geometric parameters and camera projection matrix are solved in real time, and the reconstruction results are displayed in a 3D window.

Rui Wang, Junda Wu, Yu Xia et al.

Large Language Models (LLMs) are identified as being susceptible to indirect prompt injection attack, where the model undesirably deviates from user-provided instructions by executing tasks injected in the prompt context. This vulnerability stems from LLMs' inability to distinguish between data and instructions within a prompt. In this paper, we propose CachePrune that defends against this attack by identifying and pruning task-triggering neurons from the KV cache of the input prompt context. By pruning such neurons, we encourage the LLM to treat the text spans of input prompt context as only pure data, instead of any indicator of instruction following. These neurons are identified via feature attribution with a loss function induced from an upperbound of the Direct Preference Optimization (DPO) objective. We show that such a loss function enables effective feature attribution with only a few samples. We further improve on the quality of feature attribution, by exploiting an observed triggering effect in instruction following. Our approach does not impose any formatting on the original prompt or introduce extra test-time LLM calls. Experiments show that CachePrune significantly reduces attack success rates without compromising the response quality. Note: This paper aims to defend against indirect prompt injection attacks, with the goal of developing more secure and robust AI systems.

Hao Wang, Ying Zhou, Haoyu Zhao et al.

3D Gaussian Splatting (3DGS) has emerged as a pivotal technique for real-time view synthesis in colonoscopy, enabling critical applications such as virtual colonoscopy and lesion tracking. However, the vanilla 3DGS assumes static illumination and that observed appearance depends solely on viewing angle, which causes incompatibility with the photometric variations in colonoscopic scenes induced by dynamic light source/camera. This mismatch forces most 3DGS methods to introduce structure-violating vaporous Gaussian blobs between the camera and tissues to compensate for illumination attenuation, ultimately degrading the quality of 3D reconstructions. Previous works only consider the illumination attenuation caused by light distance, ignoring the physical characters of light source and camera. In this paper, we propose ColIAGS, an improved 3DGS framework tailored for colonoscopy. To mimic realistic appearance under varying illumination, we introduce an Improved Appearance Modeling with two types of illumination attenuation factors, which enables Gaussians to adapt to photometric variations while preserving geometry accuracy. To ensure the geometry approximation condition of appearance modeling, we propose an Improved Geometry Modeling using high-dimensional view embedding to enhance Gaussian geometry attribute prediction. Furthermore, another cosine embedding input is leveraged to generate illumination attenuation solutions in an implicit manner. Comprehensive experimental results on standard benchmarks demonstrate that our proposed ColIAGS achieves the dual capabilities of novel view synthesis and accurate geometric reconstruction. It notably outperforms other state-of-the-art methods by achieving superior rendering fidelity while significantly reducing Depth MSE. Code will be available.

Kai Shao, Rui Wang, Yixue Hao et al.

Depression recognition based on physiological signals such as functional near-infrared spectroscopy (fNIRS) and electroencephalogram (EEG) has made considerable progress. However, most existing studies ignore the complementarity and semantic consistency of multimodal physiological signals under the same stimulation task in complex spatio-temporal patterns. In this paper, we introduce a multimodal physiological signals representation learning framework using Siamese architecture via multiscale contrasting for depression recognition (MRLMC). First, fNIRS and EEG are transformed into different but correlated data based on a time-domain data augmentation strategy. Then, we design a spatio-temporal contrasting module to learn the representation of fNIRS and EEG through weight-sharing multiscale spatio-temporal convolution. Furthermore, to enhance the learning of semantic representation associated with stimulation tasks, a semantic consistency contrast module is proposed, aiming to maximize the semantic similarity of fNIRS and EEG. Extensive experiments on publicly available and self-collected multimodal physiological signals datasets indicate that MRLMC outperforms the state-of-the-art models. Moreover, our proposed framework is capable of transferring to multimodal time series downstream tasks.

Rui Wang, Jun Xie, Jiacheng Han et al.

Natural image matting is a fundamental and challenging computer vision task. Conventionally, the problem is formulated as an underconstrained problem. Since the problem is ill-posed, further assumptions on the data distribution are required to make the problem well-posed. For classical matting methods, a commonly adopted assumption is the local smoothness assumption on foreground and background colors. However, the use of such assumptions was not systematically considered for deep learning based matting methods. In this work, we consider two local smoothness assumptions which can help improving deep image matting models. Based on the local smoothness assumptions, we propose three techniques, i.e., training set refinement, color augmentation and backpropagating refinement, which can improve the performance of the deep image matting model significantly. We conduct experiments to examine the effectiveness of the proposed algorithm. The experimental results show that the proposed method has favorable performance compared with existing matting methods.

Rui Wang

With the rapid development of computer graphics and vision, several three-dimensional (3D) reconstruction techniques have been proposed and used to obtain the 3D representation of objects in the form of point cloud models, mesh models, and geometric models. The cost of 3D reconstruction is declining due to the maturing of this technology, however, the inexpensive 3D reconstruction scanners on the market may not be able to generate a clear point cloud model as expected. This study systematically reviews some basic types of 3D reconstruction technology and introduces an easy implementation using a linear laser scanner, a camera, and a turntable. The implementation is based on the monovision with laser and has tested several objects like wiki and mug. The accuracy and resolution of the point cloud result are quite satisfying. It turns out everyone can build such a 3D reconstruction system with appropriate procedures.

Matheus Gadelha, Aartika Rai, Subhransu Maji et al.

We investigate the problem of learning a probabilistic distribution over three-dimensional shapes given two-dimensional views of multiple objects taken from unknown viewpoints. Our approach called projective generative adversarial network (PrGAN) trains a deep generative model of 3D shapes whose projections (or renderings) match the distributions of the provided 2D distribution. The addition of a differentiable projection module allows us to infer the underlying 3D shape distribution without access to any explicit 3D or viewpoint annotation during the learning phase. We show that our approach produces 3D shapes of comparable quality to GANs trained directly on 3D data. %for a number of shape categoriesincluding chairs, airplanes, and cars. Experiments also show that the disentangled representation of 2D shapes into geometry and viewpoint leads to a good generative model of 2D shapes. The key advantage of our model is that it estimates 3D shape, viewpoint, and generates novel views from an input image in a completely unsupervised manner. We further investigate how the generative models can be improved if additional information such as depth, viewpoint or part segmentations is available at training time. To this end, we present new differentiable projection operators that can be used by PrGAN to learn better 3D generative models. Our experiments show that our method can successfully leverage extra visual cues to create more diverse and accurate shapes.

Zhaoliang Lun, Matheus Gadelha, Evangelos Kalogerakis et al.

We propose a method for reconstructing 3D shapes from 2D sketches in the form of line drawings. Our method takes as input a single sketch, or multiple sketches, and outputs a dense point cloud representing a 3D reconstruction of the input sketch(es). The point cloud is then converted into a polygon mesh. At the heart of our method lies a deep, encoder-decoder network. The encoder converts the sketch into a compact representation encoding shape information. The decoder converts this representation into depth and normal maps capturing the underlying surface from several output viewpoints. The multi-view maps are then consolidated into a 3D point cloud by solving an optimization problem that fuses depth and normals across all viewpoints. Based on our experiments, compared to other methods, such as volumetric networks, our architecture offers several advantages, including more faithful reconstruction, higher output surface resolution, better preservation of topology and shape structure.