CVPR 2024 Papers

Portrait harmonization aims to composite a subject into a new background adjusting its lighting and color to ensure harmony with the background scene. Existing harmonization techniques often only focus on adjusting the global color and brightness of the foreground and ignore crucial illumination cues from the background such as apparent lighting direction leading to unrealistic compositions. We introduce Relightful Harmonization a lighting-aware diffusion model designed to seamlessly harmonize sophisticated lighting effect for the foreground portrait using any background image. Our approach unfolds in three stages. First we introduce a lighting representation module that allows our diffusion model to encode lighting information from target image background. Second we introduce an alignment network that aligns lighting features learned from image background with lighting features learned from panorama environment maps which is a complete representation for scene illumination. Last to further boost the photorealism of the proposed method we introduce a novel data simulation pipeline that generates synthetic training pairs from a diverse range of natural images which are used to refine the model. Our method outperforms existing benchmarks in visual fidelity and lighting coherence showing superior generalization in real-world testing scenarios highlighting its versatility and practicality.

The fidelity of relighting is bounded by both geometry and appearance representations. For geometry both mesh and volumetric approaches have difficulty modeling intricate structures like 3D hair geometry. For appearance existing relighting models are limited in fidelity and often too slow to render in real-time with high-resolution continuous environments. In this work we present Relightable Gaussian Codec Avatars a method to build high-fidelity relightable head avatars that can be animated to generate novel expressions. Our geometry model based on 3D Gaussians can capture 3D-consistent sub-millimeter details such as hair strands and pores on dynamic face sequences. To support diverse materials of human heads such as the eyes skin and hair in a unified manner we present a novel relightable appearance model based on learnable radiance transfer. Together with global illumination-aware spherical harmonics for the diffuse components we achieve real-time relighting with all-frequency reflections using spherical Gaussians. This appearance model can be efficiently relit under both point light and continuous illumination. We further improve the fidelity of eye reflections and enable explicit gaze control by introducing relightable explicit eye models. Our method outperforms existing approaches without compromising real-time performance. We also demonstrate real-time relighting of avatars on a tethered consumer VR headset showcasing the efficiency and fidelity of our avatars.

Synthesizing realistic videos of talking faces under custom lighting conditions and viewing angles benefits various downstream applications like video conferencing. However most existing relighting methods are either time-consuming or unable to adjust the viewpoints. In this paper we present the first real-time 3D-aware method for relighting in-the-wild videos of talking faces based on Neural Radiance Fields (NeRF). Given an input portrait video our method can synthesize talking faces under both novel views and novel lighting conditions with a photo-realistic and disentangled 3D representation. Specifically we infer an albedo tri-plane as well as a shading tri-plane based on a desired lighting condition for each video frame with fast dual-encoders. We also leverage a temporal consistency network to ensure smooth transitions and reduce flickering artifacts. Our method runs at 32.98 fps on consumer-level hardware and achieves state-of-the-art results in terms of reconstruction quality lighting error lighting instability temporal consistency and inference speed. We demonstrate the effectiveness and interactivity of our method on various portrait videos with diverse lighting and viewing conditions.

Vision-Language (VL) models have gained significant research focus enabling remarkable advances in multimodal reasoning. These architectures typically comprise a vision encoder a Large Language Model (LLM) and a projection module that aligns visual features with the LLM's representation space. Despite their success a critical limitation persists: the vision encoding process remains decoupled from user queries often in the form of image-related questions. Consequently the resulting visual features may not be optimally attuned to the query-specific elements of the image. To address this we introduce QA-ViT a Question Aware Vision Transformer approach for multimodal reasoning which embeds question awareness directly within the vision encoder. This integration results in dynamic visual features focusing on relevant image aspects to the posed question. QA-ViT is model-agnostic and can be incorporated efficiently into any VL architecture. Extensive experiments demonstrate the effectiveness of applying our method to various multimodal architectures leading to consistent improvement across diverse tasks and showcasing its potential for enhancing visual and scene-text understanding.

We address the problem of online action segmentation for egocentric procedural task videos. While previous studies have mostly focused on offline action segmentation where entire videos are available for both training and inference the transition to online action segmentation is crucial for practical applications like AR/VR task assistants. Notably applying an offline-trained model directly to online inference results in a significant performance drop due to the inconsistency between training and inference. We propose an online action segmentation framework by first modifying existing architectures to make them causal. Second we develop a novel action progress prediction module to dynamically estimate the progress of ongoing actions and using them to refine the predictions of causal action segmentation. Third we propose to learn task graphs from training videos and leverage them to obtain smooth and procedure-consistent segmentations. With the combination of progress and task graph with casual action segmentation our framework effectively addresses prediction uncertainty and oversegmentation in online action segmentation and achieves significant improvement on three egocentric datasets.

Material appearance is a key component of photorealism with a pronounced impact on human perception. Although there are many prior works targeting at measuring opaque materials using light-weight setups (e.g. consumer-level cameras) little attention is paid on acquiring the optical properties of translucent materials which are also quite common in nature. In this paper we present a practical method for acquiring scattering properties of translucent materials based solely on ordinary images captured with unknown lighting and camera parameters. The key to our method is an inter-pixel translucency prior which states that image pixels of a given homogeneous translucent material typically form curves (dubbed translucent curves) in the RGB space of which the shapes are determined by the parameters of the material. We leverage this prior in a specially-designed convolutional neural network comprising multiple encoders a translucency-aware feature fusion module and a cascaded decoder. We demonstrate through both visual comparisons and quantitative evaluations that high accuracy can be achieved on a wide range of real-world translucent materials.

Positive-Unlabeled (PU) learning aims to train a binary classifier using minimal positive data supplemented by a substantially larger pool of unlabeled data in the specific absence of explicitly annotated negatives. Despite its straightforward nature as a binary classification task the currently best-performing PU algorithms still largely lag behind the supervised counterpart. In this work we identify that the primary bottleneck lies in the difficulty of deriving discriminative representations under unreliable binary supervision with poor semantics which subsequently hinders the common label disambiguation procedures. To cope with this problem we propose a novel PU learning framework namely Latent Group-Aware Meta Disambiguation (LaGAM) which incorporates a hierarchical contrastive learning module to extract the underlying grouping semantics within PU data and produce compact representations. As a result LaGAM enables a more aggressive label disambiguation strategy where we enhance the robustness of training by iteratively distilling the true labels of unlabeled data directly through meta-learning. Extensive experiments show that LaGAM significantly outperforms the current state-of-the-art methods by an average of 6.8% accuracy on common benchmarks approaching the supervised baseline. We also provide comprehensive ablations as well as visualized analysis to verify the effectiveness of our LaGAM.

Establishing precise semantic correspondence across object instances in different images is a fundamental and challenging task in computer vision. In this task difficulty arises often due to three challenges: confusing regions with similar appearance inconsistent object scale and indistinguishable nearby pixels. Recognizing these challenges our paper proposes a novel semantic matching pipeline named LPMFlow toward extracting fine-grained semantics and geometry layouts for building pixel-level semantic correspondences. LPMFlow consists of three modules each addressing one of the aforementioned challenges. The layout-aware representation learning module uniformly encodes source and target tokens to distinguish pixels or regions with similar appearances but different geometry semantics. The progressive feature superresolution module outputs four sets of 4D correlation tensors to generate accurate semantic flow between objects in different scales. Finally the matching flow integration and refinement module is exploited to fuse matching flow in different scales to give the final flow predictions. The whole pipeline can be trained end-to-end with a balance of computational cost and correspondence details. Extensive experiments based on benchmarks such as SPair-71K PF-PASCAL and PF-WILLOW have proved that the proposed method can well tackle the three challenges and outperform the previous methods especially in more stringent settings. Code is available at https://github.com/YXSUNMADMAX/LPMFlow.

The credibility and practicality of a reconstructed hand-object interaction sequence depend largely on its physical plausibility. However due to high occlusions during hand-object interaction physical plausibility remains a challenging criterion for purely vision-based tracking methods. To address this issue and enhance the results of existing hand trackers this paper proposes a novel physically-aware hand motion de-noising method. Specifically we introduce two learned loss terms that explicitly capture two crucial aspects of physical plausibility: grasp credibility and manipulation feasibility. These terms are used to train a physically-aware de-noising network. Qualitative and quantitative experiments demonstrate that our approach significantly improves both fine-grained physical plausibility and overall pose accuracy surpassing current state-of-the-art de-noising methods.

While current methods have shown promising progress on estimating 3D human motion from monocular videos their motion estimates are often physically unrealistic because they mainly consider kinematics. In this paper we introduce Physics-aware Pretrained Transformer (PhysPT) which improves kinematics-based motion estimates and infers motion forces. PhysPT exploits a Transformer encoder-decoder backbone to effectively learn human dynamics in a self-supervised manner. Moreover it incorporates physics principles governing human motion. Specifically we build a physics-based body representation and contact force model. We leverage them to impose novel physics-inspired training losses (i.e. force loss contact loss and Euler-Lagrange loss) enabling PhysPT to capture physical properties of the human body and the forces it experiences. Experiments demonstrate that once trained PhysPT can be directly applied to kinematics-based estimates to significantly enhance their physical plausibility and generate favourable motion forces. Furthermore we show that these physically meaningful quantities translate into improved accuracy of an important downstream task: human action recognition.

While remarkable progress has been made on supervised skeleton-based action recognition the challenge of zero-shot recognition remains relatively unexplored. In this paper we argue that relying solely on aligning label-level semantics and global skeleton features is insufficient to effectively transfer locally consistent visual knowledge from seen to unseen classes. To address this limitation we introduce Part-aware Unified Representation between Language and Skeleton (PURLS) to explore visual-semantic alignment at both local and global scales. PURLS introduces a new prompting module and a novel partitioning module to generate aligned textual and visual representations across different levels. The former leverages a pre-trained GPT-3 to infer refined descriptions of the global and local (body-part-based and temporal-interval-based) movements from the original action labels. The latter employs an adaptive sampling strategy to group visual features from all body joint movements that are semantically relevant to a given description. Our approach is evaluated on various skeleton/language backbones and three large-scale datasets i.e. NTU-RGB+D 60 NTU-RGB+D 120 and a newly curated dataset Kinetics-skeleton 200. The results showcase the universality and superior performance of PURLS surpassing prior skeleton-based solutions and standard baselines from other domains. The source codes can be accessed at https://github.com/azzh1/PURLS.

While GAN-based models have been successful in image stylization tasks they often struggle with structure preservation while stylizing a wide range of input images. Recently diffusion models have been adopted for image stylization but still lack the capability to maintain the original quality of input images. Building on this we propose OSASIS: a novel one-shot stylization method that is robust in structure preservation. We show that OSASIS is able to effectively disentangle the semantics from the structure of an image allowing it to control the level of content and style implemented to a given input. We apply OSASIS to various experimental settings including stylization with out-of-domain reference images and stylization with text-driven manipulation. Results show that OSASIS outperforms other stylization methods especially for input images that were rarely encountered during training providing a promising solution to stylization via diffusion models.

The scarcity of ground-truth labels poses one major challenge in developing optical flow estimation models that are both generalizable and robust. While current methods rely on data augmentation they have yet to fully exploit the rich information available in labeled video sequences. We propose OCAI a method that supports robust frame interpolation by generating intermediate video frames alongside optical flows in between. Utilizing a forward warping approach OCAI employs occlusion awareness to resolve ambiguities in pixel values and fills in missing values by leveraging the forward-backward consistency of optical flows. Additionally we introduce a teacher-student style semi-supervised learning method on top of the interpolated frames. Using a pair of unlabeled frames and the teacher model's predicted optical flow we generate interpolated frames and flows to train a student model. The teacher's weights are maintained using Exponential Moving Averaging of the student. Our evaluations demonstrate perceptually superior interpolation quality and enhanced optical flow accuracy on established benchmarks such as Sintel and KITTI.

Semantic scene completion also known as semantic occupancy prediction can provide dense geometric and semantic information for autonomous vehicles which attracts the increasing attention of both academia and industry. Unfortunately existing methods usually formulate this task as a voxel-wise classification problem and treat each voxel equally in 3D space during training. As the hard voxels have not been paid enough attention the performance in some challenging regions is limited. The 3D dense space typically contains a large number of empty voxels which are easy to learn but require amounts of computation due to handling all the voxels uniformly for the existing models. Furthermore the voxels in the boundary region are more challenging to differentiate than those in the interior. In this paper we propose HASSC approach to train the semantic scene completion model with hardness-aware design. The global hardness from the network optimization process is defined for dynamical hard voxel selection. Then the local hardness with geometric anisotropy is adopted for voxel-wise refinement. Besides self-distillation strategy is introduced to make training process stable and consistent. Extensive experiments show that our HASSC scheme can effectively promote the accuracy of the baseline model without incurring the extra inference cost. Source code is available at: https://github.com/songw-zju/HASSC.

Layout-aware text-to-image generation is a task to generate multi-object images that reflect layout conditions in addition to text conditions. The current layout-aware text-to-image diffusion models still have several issues including mismatches between the text and layout conditions and quality degradation of generated images. This paper proposes a novel layout-aware text-to-image diffusion model called NoiseCollage to tackle these issues. During the denoising process NoiseCollage independently estimates noises for individual objects and then crops and merges them into a single noise. This operation helps avoid condition mismatches; in other words it can put the right objects in the right places. Qualitative and quantitative evaluations show that NoiseCollage outperforms several state-of-the-art models. These successful results indicate that the crop-and-merge operation of noises is a reasonable strategy to control image generation. We also show that NoiseCollage can be integrated with ControlNet to use edges sketches and pose skeletons as additional conditions. Experimental results show that this integration boosts the layout accuracy of ControlNet. The code is available at https://github.com/univ-esuty/noisecollage.

We introduce MultiPhys a method designed for recovering multi-person motion from monocular videos. Our focus lies in capturing coherent spatial placement between pairs of individuals across varying degrees of engagement. MultiPhys being physically aware exhibits robustness to jittering and occlusions and effectively eliminates penetration issues between the two individuals. We devise a pipeline in which the motion estimated by a kinematic-based method is fed into a physics simulator in an autoregressive manner. We introduce distinct components that enable our model to harness the simulator's properties without compromising the accuracy of the kinematic estimates. This results in final motion estimates that are both kinematically coherent and physically compliant. Extensive evaluations on three challenging datasets characterized by substantial inter-person interaction show that our method significantly reduces errors associated with penetration and foot skating while performing competitively with the state-of-the-art on motion accuracy and smoothness.

Collaborative perception allows for information sharing between multiple agents such as vehicles and infrastructure to obtain a comprehensive view of the environment through communication and fusion. Current research on multi-agent collaborative perception systems often assumes ideal communication and perception environments and neglects the effect of real-world noise such as pose noise motion blur and perception noise. To address this gap in this paper we propose a novel motion-aware robust communication network (MRCNet) that mitigates noise interference and achieves accurate and robust collaborative perception. MRCNet consists of two main components: multi-scale robust fusion (MRF) addresses pose noise by developing cross-semantic multi-scale enhanced aggregation to fuse features of different scales while motion enhanced mechanism (MEM) captures motion context to compensate for information blurring caused by moving objects. Experimental results on popular collaborative 3D object detection datasets demonstrate that MRCNet outperforms competing methods in noisy scenarios with improved perception performance using less bandwidth.

Existing diffusion-based video editing models have made gorgeous advances for editing attributes of a source video over time but struggle to manipulate the motion information while preserving the original protagonist's appearance and background. To address this we propose MotionEditor the first diffusion model for video motion editing. MotionEditor incorporates a novel content-aware motion adapter into ControlNet to capture temporal motion correspondence. While ControlNet enables direct generation based on skeleton poses it encounters challenges when modifying the source motion in the inverted noise due to contradictory signals between the noise (source) and the condition (reference). Our adapter complements ControlNet by involving source content to transfer adapted control signals seamlessly. Further we build up a two-branch architecture (a reconstruction branch and an editing branch) with a high-fidelity attention injection mechanism facilitating branch interaction. This mechanism enables the editing branch to query the key and value from the reconstruction branch in a decoupled manner making the editing branch retain the original background and protagonist appearance. We also propose a skeleton alignment algorithm to address the discrepancies in pose size and position. Experiments demonstrate the promising motion editing ability of MotionEditor both qualitatively and quantitatively. To the best of our knowledge MotionEditor is the first to use diffusion models specifically for video motion editing considering the origin dynamic background and camera movement.

3D visual grounding involves matching natural language descriptions with their corresponding objects in 3D spaces. Existing methods often face challenges with accuracy in object recognition and struggle in interpreting complex linguistic queries particularly with descriptions that involve multiple anchors or are view-dependent. In response we present the MiKASA (Multi-Key-Anchor Scene-Aware) Transformer. Our novel end-to-end trained model integrates a self-attention-based scene-aware object encoder and an original multi-key-anchor technique enhancing object recognition accuracy and the understanding of spatial relationships. Furthermore MiKASA improves the explainability of decision-making facilitating error diagnosis. Our model achieves the highest overall accuracy in the Referit3D challenge for both the Sr3D and Nr3D datasets particularly excelling by a large margin in categories that require viewpoint-dependent descriptions.