Diffusion models (DMs) excel in photo-realistic image synthesis, but their adaptation to LiDAR scene generation poses a substantial hurdle. This is primarily because DMs operating in the point space struggle to preserve the curve-like patterns and 3D geometry of LiDAR scenes, which consumes much of their representation power. In this paper, we propose LiDAR Diffusion Models (LiDMs) to generate LiDAR-realistic scenes from a latent space tailored to capture the realism of LiDAR scenes by incorporating geometric priors into the learning pipeline. Our method targets three major desiderata: pattern realism, geometry realism, and object realism. Specifically, we introduce curve-wise compression to simulate real-world LiDAR patterns, point-wise coordinate supervision to learn scene geometry, and patch-wise encoding for a full 3D object context. With these three core designs, our method achieves competitive performance on unconditional LiDAR generation in 64-beam scenario and state of the art on conditional LiDAR generation, while maintaining high efficiency compared to point-based DMs (up to 107$\times$ faster). Furthermore, by compressing LiDAR scenes into a latent space, we enable the controllability of DMs with various conditions such as semantic maps, camera views, and text prompts. Our code and pretrained weights are available at https://github.com/hancyran/LiDAR-Diffusion.
Constructing photo-realistic Free-Viewpoint Videos (FVVs) of dynamic scenes from multi-view videos remains a challenging endeavor. Despite the remarkable advancements achieved by current neural rendering techniques, these methods generally require complete video sequences for offline training and are not capable of real-time rendering. To address these constraints, we introduce 3DGStream, a method designed for efficient FVV streaming of real-world dynamic scenes. Our method achieves fast on-the-fly per-frame reconstruction within 12 seconds and real-time rendering at 200 FPS. Specifically, we utilize 3D Gaussians (3DGs) to represent the scene. Instead of the na\"ive approach of directly optimizing 3DGs per-frame, we employ a compact Neural Transformation Cache (NTC) to model the translations and rotations of 3DGs, markedly reducing the training time and storage required for each FVV frame. Furthermore, we propose an adaptive 3DG addition strategy to handle emerging objects in dynamic scenes. Experiments demonstrate that 3DGStream achieves competitive performance in terms of rendering speed, image quality, training time, and model storage when compared with state-of-the-art methods.
Achieving an effective fine-grained appearance variation over 2D facial images, whilst preserving facial identity, is a challenging task due to the high complexity and entanglement of common 2D facial feature encoding spaces. Despite these challenges, such fine-grained control, by way of disentanglement is a crucial enabler for data-driven racial bias mitigation strategies across multiple automated facial analysis tasks, as it allows to analyse, characterise and synthesise human facial diversity. In this paper, we propose a novel GAN framework to enable fine-grained control over individual race-related phenotype attributes of the facial images. Our framework factors the latent (feature) space into elements that correspond to race-related facial phenotype representations, thereby separating phenotype aspects (e.g. skin, hair colour, nose, eye, mouth shapes), which are notoriously difficult to annotate robustly in real-world facial data. Concurrently, we also introduce a high quality augmented, diverse 2D face image dataset drawn from CelebA-HQ for GAN training. Unlike prior work, our framework only relies upon 2D imagery and related parameters to achieve state-of-the-art individual control over race-related phenotype attributes with improved photo-realistic output.
We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. Unlike current general-purpose foundation models that are stuck in the dilemma of inferior quality and text-image misalignment for humans, CosmicMan enables generating photo-realistic human images with meticulous appearance, reasonable structure, and precise text-image alignment with detailed dense descriptions. At the heart of CosmicMan's success are the new reflections and perspectives on data and models: (1) We found that data quality and a scalable data production flow are essential for the final results from trained models. Hence, we propose a new data production paradigm, Annotate Anyone, which serves as a perpetual data flywheel to produce high-quality data with accurate yet cost-effective annotations over time. Based on this, we constructed a large-scale dataset, CosmicMan-HQ 1.0, with 6 Million high-quality real-world human images in a mean resolution of 1488x1255, and attached with precise text annotations deriving from 115 Million attributes in diverse granularities. (2) We argue that a text-to-image foundation model specialized for humans must be pragmatic -- easy to integrate into down-streaming tasks while effective in producing high-quality human images. Hence, we propose to model the relationship between dense text descriptions and image pixels in a decomposed manner, and present Decomposed-Attention-Refocusing (Daring) training framework. It seamlessly decomposes the cross-attention features in existing text-to-image diffusion model, and enforces attention refocusing without adding extra modules. Through Daring, we show that explicitly discretizing continuous text space into several basic groups that align with human body structure is the key to tackling the misalignment problem in a breeze.
We propose a generative model that, given a coarsely edited image, synthesizes a photorealistic output that follows the prescribed layout. Our method transfers fine details from the original image and preserves the identity of its parts. Yet, it adapts it to the lighting and context defined by the new layout. Our key insight is that videos are a powerful source of supervision for this task: objects and camera motions provide many observations of how the world changes with viewpoint, lighting, and physical interactions. We construct an image dataset in which each sample is a pair of source and target frames extracted from the same video at randomly chosen time intervals. We warp the source frame toward the target using two motion models that mimic the expected test-time user edits. We supervise our model to translate the warped image into the ground truth, starting from a pretrained diffusion model. Our model design explicitly enables fine detail transfer from the source frame to the generated image, while closely following the user-specified layout. We show that by using simple segmentations and coarse 2D manipulations, we can synthesize a photorealistic edit faithful to the user's input while addressing second-order effects like harmonizing the lighting and physical interactions between edited objects.
Text-to-image (T2I) generative models have recently emerged as a powerful tool, enabling the creation of photo-realistic images and giving rise to a multitude of applications. However, the effective integration of T2I models into fundamental image classification tasks remains an open question. A prevalent strategy to bolster image classification performance is through augmenting the training set with synthetic images generated by T2I models. In this study, we scrutinize the shortcomings of both current generative and conventional data augmentation techniques. Our analysis reveals that these methods struggle to produce images that are both faithful (in terms of foreground objects) and diverse (in terms of background contexts) for domain-specific concepts. To tackle this challenge, we introduce an innovative inter-class data augmentation method known as Diff-Mix (https://github.com/Zhicaiwww/Diff-Mix), which enriches the dataset by performing image translations between classes. Our empirical results demonstrate that Diff-Mix achieves a better balance between faithfulness and diversity, leading to a marked improvement in performance across diverse image classification scenarios, including few-shot, conventional, and long-tail classifications for domain-specific datasets.
This paper, for the first time, explores text-to-image diffusion models for Zero-Shot Sketch-based Image Retrieval (ZS-SBIR). We highlight a pivotal discovery: the capacity of text-to-image diffusion models to seamlessly bridge the gap between sketches and photos. This proficiency is underpinned by their robust cross-modal capabilities and shape bias, findings that are substantiated through our pilot studies. In order to harness pre-trained diffusion models effectively, we introduce a straightforward yet powerful strategy focused on two key aspects: selecting optimal feature layers and utilising visual and textual prompts. For the former, we identify which layers are most enriched with information and are best suited for the specific retrieval requirements (category-level or fine-grained). Then we employ visual and textual prompts to guide the model's feature extraction process, enabling it to generate more discriminative and contextually relevant cross-modal representations. Extensive experiments on several benchmark datasets validate significant performance improvements.
Neural radiance fields (NeRFs) show potential for transforming images captured worldwide into immersive 3D visual experiences. However, most of this captured visual data remains siloed in our camera rolls as these images contain personal details. Even if made public, the problem of learning 3D representations of billions of scenes captured daily in a centralized manner is computationally intractable. Our approach, DecentNeRF, is the first attempt at decentralized, crowd-sourced NeRFs that require $\sim 10^4\times$ less server computing for a scene than a centralized approach. Instead of sending the raw data, our approach requires users to send a 3D representation, distributing the high computation cost of training centralized NeRFs between the users. It learns photorealistic scene representations by decomposing users' 3D views into personal and global NeRFs and a novel optimally weighted aggregation of only the latter. We validate the advantage of our approach to learn NeRFs with photorealism and minimal server computation cost on structured synthetic and real-world photo tourism datasets. We further analyze how secure aggregation of global NeRFs in DecentNeRF minimizes the undesired reconstruction of personal content by the server.
Vision-and-Language Navigation (VLN) is a challenging task that requires a robot to navigate in photo-realistic environments with human natural language promptings. Recent studies aim to handle this task by constructing the semantic spatial map representation of the environment, and then leveraging the strong ability of reasoning in large language models for generalizing code for guiding the robot navigation. However, these methods face limitations in instance-level and attribute-level navigation tasks as they cannot distinguish different instances of the same object. To address this challenge, we propose a new method, namely, Instance-aware Visual Language Map (IVLMap), to empower the robot with instance-level and attribute-level semantic mapping, where it is autonomously constructed by fusing the RGBD video data collected from the robot agent with special-designed natural language map indexing in the bird's-in-eye view. Such indexing is instance-level and attribute-level. In particular, when integrated with a large language model, IVLMap demonstrates the capability to i) transform natural language into navigation targets with instance and attribute information, enabling precise localization, and ii) accomplish zero-shot end-to-end navigation tasks based on natural language commands. Extensive navigation experiments are conducted. Simulation results illustrate that our method can achieve an average improvement of 14.4\% in navigation accuracy. Code and demo are released at https://ivlmap.github.io/.
Recent works often assume that Vision-Language Model (VLM) representations are based on visual attributes like shape. However, it is unclear to what extent VLMs prioritize this information to represent concepts. We propose Extract and Explore (EX2), a novel approach to characterize important textual features for VLMs. EX2 uses reinforcement learning to align a large language model with VLM preferences and generates descriptions that incorporate the important features for the VLM. Then, we inspect the descriptions to identify the features that contribute to VLM representations. We find that spurious descriptions have a major role in VLM representations despite providing no helpful information, e.g., Click to enlarge photo of CONCEPT. More importantly, among informative descriptions, VLMs rely significantly on non-visual attributes like habitat to represent visual concepts. Also, our analysis reveals that different VLMs prioritize different attributes in their representations. Overall, we show that VLMs do not simply match images to scene descriptions and that non-visual or even spurious descriptions significantly influence their representations.