CVPR 2024 Papers

Despite exciting progress in automatic 3D reconstruction from images excessive and irregular triangular faces in the resulting meshes still constitute a significant challenge when it comes to adoption in practical artist workflows. Therefore we propose a method to extract regular quad-dominant meshes from posed images. More specifically we generate a high-quality 3D model through decomposition into an easily editable quad-dominant mesh with pixel-level details such as displacement materials and lighting. To enable end-to-end learning of shape and quad topology we QUADify a neural implicit representation using our novel differentiable re-meshing objective. Distinct from previous work our method exploits artifact-free Catmull-Clark subdivision combined with vertex displacement to extract pixel-level details linked to the base geometry. Finally we apply differentiable rendering techniques for material and lighting decomposition to optimize for image reconstruction. Our experiments show the benefits of end-to-end re-meshing and that our method yields state-of-the-art geometric accuracy while providing lightweight meshes with displacements and textures that are directly compatible with professional renderers and game engines.

Adding artificial patterns to objects like QR codes can ease tasks such as object tracking robot navigation and conveying information (e.g. a label or a website link). However these patterns require a physical application and they alter the object's appearance. Conversely projected patterns can temporarily change the object's appearance aiding tasks like 3D scanning and retrieving object textures and shading. However projected patterns impede dynamic tasks like object tracking because they do not `stick' to the object's surface. Or do they? This paper introduces a novel approach combining the advantages of projected and persistent physical patterns. Our system projects heat patterns using a laser beam (similar in spirit to a LIDAR) which a thermal camera observes and tracks. Such thermal patterns enable tracking poorly-textured objects whose tracking is highly challenging with standard cameras while not affecting the object's appearance or physical properties. To avail these thermal patterns in existing vision frameworks we train a network to reverse heat diffusion's effects and remove inconsistent pattern points between different thermal frames. We prototyped and tested this approach on dynamic vision tasks like structure from motion optical flow and object tracking of everyday textureless objects.

Zero-shot learning (ZSL) recognizes the unseen classes by conducting visual-semantic interactions to transfer semantic knowledge from seen classes to unseen ones supported by semantic information (e.g. attributes). However existing ZSL methods simply extract visual features using a pre-trained network backbone (i.e. CNN or ViT) which fail to learn matched visual-semantic correspondences for representing semantic-related visual features as lacking of the guidance of semantic information resulting in undesirable visual-semantic interactions. To tackle this issue we propose a progressive semantic-guided vision transformer for zero-shot learning (dubbed ZSLViT). ZSLViT mainly considers two properties in the whole network: i) discover the semantic-related visual representations explicitly and ii) discard the semantic-unrelated visual information. Specifically we first introduce semantic-embedded token learning to improve the visual-semantic correspondences via semantic enhancement and discover the semantic-related visual tokens explicitly with semantic-guided token attention. Then we fuse low semantic-visual correspondence visual tokens to discard the semantic-unrelated visual information for visual enhancement. These two operations are integrated into various encoders to progressively learn semantic-related visual representations for accurate visual-semantic interactions in ZSL. The extensive experiments show that our ZSLViT achieves significant performance gains on three popular benchmark datasets i.e. CUB SUN and AWA2.

The use of models that have been pre-trained on natural image datasets like ImageNet may face some limitations. First this use may be restricted due to copyright and license on the training images and privacy laws. Second these datasets and models may incorporate societal and ethical biases. Formula-driven supervised learning (FDSL) enables model pre-training to circumvent these issues. This consists of generating a synthetic image dataset based on mathematical formulae and pre-training the model on it. In this work we propose novel FDSL datasets based on Mandelbulb Variations. These datasets contain RGB images that are projections of colored objects deriving from the 3D Mandelbulb fractal. Pre-training ResNet-50 on one of our proposed datasets MandelbulbVAR-1k enables an average top-1 accuracy over target classification datasets that is at least 1% higher than pre-training on existing FDSL datasets. With regard to anomaly detection on MVTec AD pre-training the WideResNet-50 backbone on MandelbulbVAR-1k enables PatchCore to achieve 97.2% average image-level AUROC. This is only 1.9% lower than pre-training on ImageNet-1k (99.1%) and 4.5% higher than pre-training on the second-best performing FDSL dataset i.e. VisualAtom-1k (92.7%). Regarding Vision Transformer (ViT) pre-training another dataset that we propose and coin MandelbulbVAR-Hybrid-21k enables ViT-Base to achieve 82.2% top-1 accuracy on ImageNet-1k which is 0.4% higher than pre-training on ImageNet-21k (81.8%) and only 0.1% lower than pre-training on VisualAtom-1k (82.3%).

Few-Shot Class Incremental Learning (FSCIL) is a task that requires a model to learn new classes incrementally without forgetting when only a few samples for each class are given. FSCIL encounters two significant challenges: catastrophic forgetting and overfitting and these challenges have driven prior studies to primarily rely on shallow models such as ResNet-18. Even though their limited capacity can mitigate both forgetting and overfitting issues it leads to inadequate knowledge transfer during few-shot incremental sessions. In this paper we argue that large models such as vision and language transformers pre-trained on large datasets can be excellent few-shot incremental learners. To this end we propose a novel FSCIL framework called PriViLege Pre-trained Vision and Language transformers with prompting functions and knowledge distillation. Our framework effectively addresses the challenges of catastrophic forgetting and overfitting in large models through new pre-trained knowledge tuning (PKT) and two losses: entropy-based divergence loss and semantic knowledge distillation loss. Experimental results show that the proposed PriViLege significantly outperforms the existing state-of-the-art methods with a large margin e.g. +9.38% in CUB200 +20.58% in CIFAR-100 and +13.36% in miniImageNet. Our implementation code is available at https://github.com/KHU-AGI/PriViLege.

Existing one-shot 4D head synthesis methods usually learn from monocular videos with the aid of 3DMM reconstruction yet the latter is evenly challenging which restricts them from reasonable 4D head synthesis. We present a method to learn one-shot 4D head synthesis via large-scale synthetic data. The key is to first learn a part-wise 4D generative model from monocular images via adversarial learning to synthesize multi-view images of diverse identities and full motions as training data; then leverage a transformer-based animatable triplane reconstructor to learn 4D head reconstruction using the synthetic data. A novel learning strategy is enforced to enhance the generalizability to real images by disentangling the learning process of 3D reconstruction and reenactment. Experiments demonstrate our superiority over the prior art.

Lidar has become a cornerstone sensing modality for 3D vision especially for large outdoor scenarios and autonomous driving. Conventional lidar sensors are capable of providing centimeter-accurate distance information by emitting laser pulses into a scene and measuring the time-of-flight (ToF) of the reflection. However the polarization of the received light that depends on the surface orientation and material properties is usually not considered. As such the polarization modality has the potential to improve scene reconstruction beyond distance measurements. In this work we introduce a novel long-range polarization wavefront lidar sensor (PolLidar) that modulates the polarization of the emitted and received light. Departing from conventional lidar sensors PolLidar allows access to the raw time-resolved polarimetric wavefronts. We leverage polarimetric wavefronts to estimate normals distance and material properties in outdoor scenarios with a novel learned reconstruction method. To train and evaluate the method we introduce a simulated and real-world long-range dataset with paired raw lidar data ground truth distance and normal maps. We find that the proposed method improves normal and distance reconstruction by 53% mean angular error and 41% mean absolute error compared to existing shape-from-polarization (SfP) and ToF methods. Code and data are open-sourced here.

In radio astronomy visibility data which are measurements of wave signals from radio telescopes are transformed into images for observation of distant celestial objects. However these resultant images usually contain both real sources and artifacts due to signal sparsity and other factors. One way to obtain cleaner images is to reconstruct samples into dense forms before imaging. Unfortunately existing reconstruction methods often miss some components of visibility in frequency domain so blurred object edges and persistent artifacts remain in the images. Furthermore the computation overhead is high on irregular visibility samples due to the data skew. To address these problems we propose PolarRec a transformer-encoder-conditioned reconstruction pipeline with visibility samples converted into the polar coordinate system. This coordinate system matches the way in which radio telescopes observe a celestial area as the Earth rotates. As a result visibility samples distribute in the polar system more uniformly than in the Cartesian space. Therefore we propose to use radial distance in the loss function to help reconstruct complete visibility effectively. Also we group visibility samples by their polar angles and propose a group-based encoding scheme to improve the efficiency. Our experiments demonstrate that PolarRec markedly improves imaging results by faithfully reconstructing all frequency components in the visibility domain while significantly reducing the computation cost in visibility data encoding. The code is available at https://github.com/RapidsAtHKUST/PolarRec.

We present PointInfinity an efficient family of point cloud diffusion models. Our core idea is to use a transformer-based architecture with a fixed-size resolution-invariant latent representation. This enables efficient training with low-resolution point clouds while allowing high-resolution point clouds to be generated during inference. More importantly we show that scaling the test-time resolution beyond the training resolution improves the fidelity of generated point clouds and surfaces. We analyze this phenomenon and draw a link to classifier-free guidance commonly used in diffusion models demonstrating that both allow trading off fidelity and variability during inference. Experiments on CO3D show that PointInfinity can efficiently generate high-resolution point clouds (up to 131k points 31 times more than Point-E) with state-of-the-art quality.

This paper is not motivated to seek innovation within the attention mechanism. Instead it focuses on overcoming the existing trade-offs between accuracy and efficiency within the context of point cloud processing leveraging the power of scale. Drawing inspiration from recent advances in 3D large-scale representation learning we recognize that model performance is more influenced by scale than by intricate design. Therefore we present Point Transformer V3 (PTv3) which prioritizes simplicity and efficiency over the accuracy of certain mechanisms that are minor to the overall performance after scaling such as replacing the precise neighbor search by KNN with an efficient serialized neighbor mapping of point clouds organized with specific patterns. This principle enables significant scaling expanding the receptive field from 16 to 1024 points while remaining efficient (a 3x increase in processing speed and a 10x improvement in memory efficiency compared with its predecessor PTv2). PTv3 attains state-of-the-art results on over 20 downstream tasks that span both indoor and outdoor scenarios. Further enhanced with multi-dataset joint training PTv3 pushes these results to a higher level.

Pre-training a model and then fine-tuning it on downstream tasks has demonstrated significant success in the 2D image and NLP domains. However due to the unordered and non-uniform density characteristics of point clouds it is non-trivial to explore the prior knowledge of point clouds and pre-train a point cloud backbone. In this paper we propose a novel pre-training method called Point cloud Diffusion pre-training PointDif. We consider the point cloud pre-training task as a conditional point-to-point generation problem and introduce a conditional point generator. This generator aggregates the features extracted by the backbone and employs them as the condition to guide the point-to-point recovery from the noisy point cloud thereby assisting the backbone in capturing both local and global geometric priors as well as the global point density distribution of the object. We also present a recurrent uniform sampling optimization strategy which enables the model to uniformly recover from various noise levels and learn from balanced supervision. Our PointDif achieves substantial improvement across various real-world datasets for diverse downstream tasks such as classification segmentation and detection. Specifically PointDif attains 70.0% mIoU on S3DIS Area 5 for the segmentation task and achieves an average improvement of 2.4% on ScanObjectNN for the classification task compared to TAP. Furthermore our pre-training framework can be flexibly applied to diverse point cloud backbones and bring considerable gains. Code is available at https://github.com/zhengxiaozx/PointDif

3D reconstruction from a single-view is challenging because of the ambiguity from monocular cues and lack of information about occluded regions. Neural radiance fields (NeRF) while popular for view synthesis and 3D reconstruction are typically reliant on multi-view images. Existing methods for single-view 3D reconstruction with NeRF rely on either data priors to hallucinate views of occluded regions which may not be physically accurate or shadows observed by RGB cameras which are difficult to detect in ambient light and low albedo backgrounds. We propose using time-of-flight data captured by a single-photon avalanche diode to overcome these limitations. Our method models two-bounce optical paths with NeRF using lidar transient data for supervision. By leveraging the advantages of both NeRF and two-bounce light measured by lidar we demonstrate that we can reconstruct visible and occluded geometry without data priors or reliance on controlled ambient lighting or scene albedo. In addition we demonstrate improved generalization under practical constraints on sensor spatial- and temporal-resolution. We believe our method is a promising direction as single-photon lidars become ubiquitous on consumer devices such as phones tablets and headsets.

3D reconstruction of dynamic scenes is a long-standing problem in computer graphics and increasingly difficult the less information is available. Shape-from-Template (SfT) methods aim to reconstruct a template-based geometry from RGB images or video sequences often leveraging just a single monocular camera without depth information such as regular smartphone recordings. Unfortunately existing reconstruction methods are either unphysical and noisy or slow in optimization. To solve this problem we propose a novel SfT reconstruction algorithm for cloth using a pre-trained neural surrogate model that is fast to evaluate stable and produces smooth reconstructions due to a regularizing physics simulation. Differentiable rendering of the simulated mesh enables pixel-wise comparisons between the reconstruction and a target video sequence that can be used for a gradient-based optimization procedure to extract not only shape information but also physical parameters such as stretching shearing or bending stiffness of the cloth. This allows to retain a precise stable and smooth reconstructed geometry while reducing the runtime by a factor of 400-500 compared to ?-SfT a state-of-the-art physics-based SfT approach.

Can computers perceive the physical properties of objects solely through vision? Research in cognitive science and vision science has shown that humans excel at identifying materials and estimating their physical properties based purely on visual appearance. In this paper we present a novel approach for dense prediction of the physical properties of objects using a collection of images. Inspired by how humans reason about physics through vision we leverage large language models to propose candidate materials for each object. We then construct a language-embedded point cloud and estimate the physical properties of each 3D point using a zero-shot kernel regression approach. Our method is accurate annotation-free and applicable to any object in the open world. Experiments demonstrate the effectiveness of the proposed approach in various physical property reasoning tasks such as estimating the mass of common objects as well as other properties like friction and hardness.

High dynamic range (HDR) rendering has the ability to faithfully reproduce the wide luminance ranges in natural scenes but how to accurately assess the rendering quality is relatively underexplored. Existing quality models are mostly designed for low dynamic range (LDR) images and do not align well with human perception of HDR image quality. To fill this gap we propose a family of HDR quality metrics in which the key step is employing a simple inverse display model to decompose an HDR image into a stack of LDR images with varying exposures. Subsequently these decomposed images are assessed through well-established LDR quality metrics. Our HDR quality models present three distinct benefits. First they directly inherit the recent advancements of LDR quality metrics. Second they do not rely on human perceptual data of HDR image quality for re-calibration. Third they facilitate the alignment and prioritization of specific luminance ranges for more accurate and detailed quality assessment. Experimental results show that our HDR quality metrics consistently outperform existing models in terms of quality assessment on four HDR image quality datasets and perceptual optimization of HDR novel view synthesis.

We introduce the Panoptic 3D Reconstruction task a unified and holistic scene understanding task for a monocular video. And we present PanoRecon - a novel framework to address this new task which realizes an online geometry reconstruction alone with dense semantic and instance labeling. Specifically PanoRecon incrementally performs panoptic 3D reconstruction for each video fragment consisting of multiple consecutive key frames from a volumetric feature representation using feed-forward neural networks. We adopt a depth-guided back-projection strategy to sparse and purify the volumetric feature representation. We further introduce a voxel clustering module to get object instances in each local fragment and then design a tracking and fusion algorithm for the integration of instances from different fragments to ensure temporal coherence. Such design enables our PanoRecon to yield a coherent and accurate panoptic 3D reconstruction. Experiments on ScanNetV2 demonstrate a very competitive geometry reconstruction result compared with state-of-the-art reconstruction methods as well as promising 3D panoptic segmentation result with only RGB input while being real-time. Code is available at: https://github.com/Riser6/PanoRecon.

With photo-realistic image generation Neural Radiance Field (NeRF) is widely used for large-scale dynamic scene reconstruction as autonomous driving simulator. However large-scale scene reconstruction still suffers from extremely long training time and rendering time. Low-resolution (LR) rendering combined with upsampling can alleviate this problem but it degrades image quality. In this paper we design a lightweight reference decoder which exploits prior information from known views to improve image reconstruction quality of new views. In addition to speed up prior information search we propose an optical flow and structural similarity based prior information search method. Results on KITTI and VKITTI2 datasets show that our method significantly outperforms the baseline method in terms of training speed rendering speed and rendering quality.

Recent temporal LiDAR-based 3D object detectors achieve promising performance based on the two-stage proposal-based approach. They generate 3D box candidates from the first-stage dense detector followed by different temporal aggregation methods. However these approaches require per-frame objects or whole point clouds posing challenges related to memory bank utilization. Moreover point clouds and trajectory features are combined solely based on concatenation which may neglect effective interactions between them. In this paper we propose a point-trajectory transformer with long short-term memory for efficient temporal 3D object detection. To this end we only utilize point clouds of current-frame objects and their historical trajectories as input to minimize the memory bank storage requirement. Furthermore we introduce modules to encode trajectory features focusing on long short-term and future-aware perspectives and then effectively aggregate them with point cloud features. We conduct extensive experiments on the large-scale Waymo dataset to demonstrate that our approach performs well against state-of-the-art methods. The source codes and trained models will be made publicly available. Code and models will be made publicly available at https://github.com/kuanchihhuang/PTT.

High-quality human reconstruction and photo-realistic rendering of a dynamic scene is a long-standing problem in computer vision and graphics. Despite considerable efforts invested in developing various capture systems and reconstruction algorithms recent advancements still struggle with loose or oversized clothing and overly complex poses. In part this is due to the challenges of acquiring high-quality human datasets. To facilitate the development of these fields in this paper we present PKU-DyMVHumans a versatile human-centric dataset for high-fidelity reconstruction and rendering of dynamic human scenarios from dense multi-view videos. It comprises 8.2 million frames captured by more than 56 synchronized cameras across diverse scenarios. These sequences comprise 32 human subjects across 45 different scenarios each with a high-detailed appearance and realistic human motion. Inspired by recent advancements in neural radiance field (NeRF)-based scene representations we carefully set up an off-the-shelf framework that is easy to provide those state-of-the-art NeRF-based implementations and benchmark on PKU-DyMVHumans dataset. It is paving the way for various applications like fine-grained foreground/background decomposition high-quality human reconstruction and photo-realistic novel view synthesis of a dynamic scene. Extensive studies are performed on the benchmark demonstrating new observations and challenges that emerge from using such high-fidelity dynamic data. The project page and data is available at: https://pku-dymvhumans.github.io.