Recent advancements in Large Video Language Models (LVLMs) have highlighted their potential for multi-modal understanding, yet evaluating their factual grounding in videos remains a critical unsolved challenge. To address this gap, we introduce Video SimpleQA, the first comprehensive benchmark tailored for factuality evaluation in video contexts. Our work differs from existing video benchmarks through the following key features: 1) Knowledge required: demanding integration of external knowledge beyond the video’s explicit narrative; 2) Multi-hop fact-seeking question: Each question involves multiple explicit facts and requires strict factual grounding without hypothetical or subjective inferences. We include per-hop single-fact-based sub-QAs alongside final QAs to enable fine-grained, step-by-step evaluation; 3) Short-form definitive answer: Answers are crafted as unambiguous and definitively correct in a short format with minimal scoring variance; 4) Temporal grounded required: Requiring answers to rely on one or more temporal segments in videos, rather than single frames. We extensively evaluate 33 state-of-the-art LVLMs and summarize key findings as follows: 1) Current LVLMs exhibit notable deficiencies in factual adherence, with the best-performing model o3 merely achieving an F-score of 66.3%; 2) Most LVLMs are overconfident in what they generate, with self-stated confidence exceeding actual accuracy; 3) Retrieval-Augmented Generation demonstrates consistent improvements at the cost of additional inference time overhead; 4) Multi-hop QA demonstrates substantially degraded performance compared to single-hop sub-QAs, with first-hop object/event recognition emerging as the primary bottleneck. We position Video SimpleQA as the cornerstone benchmark for video factuality assessment, aiming to steer LVLM development toward verifiable grounding in real-world contexts.

We present 360Explorer, a novel approach for generating 4D controllable panoramic videos conditioned on user-provided 3D instructions for exploring and manipulating dynamic worlds. Compared to existing perspective-based methods struggle to address spatial consistency during camera rotation in place, we introduce the panoramic view in controllable video generation models to inherently maintain the view recall consistency. By introducing dynamic point clouds as the 4D scene representations, 360Explorer unifies the modeling of camera transformations and object movements as incomplete renders to describe precise control instructions in 3D worlds. To tackle the data limitation in acquiring multi-viewpoint panoramic videos, we further propose a reverse warping strategy to construct the training dataset on easily accessible monocular panoramic videos. Extensive experiments demonstrate that 360Explorer achieves superior performance in creating 4D controllable panoramic videos with camera transformation and object movements aligned with diverse provided instructions.

3D Gaussian Splatting (3DGS) achieves impressive quality and rendering speed, but with millions of 3D Gaussians and significant storage and transmission costs. In this paper, we aim to develop a simple yet effective method called NeuralGS that compresses the original 3DGS into a compact representation. Our observation is that neural fields like NeRF can represent complex 3D scenes with Multi-Layer Perceptron (MLP) neural networks using only a few megabytes. Thus, NeuralGS effectively adopts the neural field representation to encode the attributes of 3D Gaussians with MLPs, only requiring a small storage size even for a large-scale scene. To achieve this, we adopt a clustering strategy and fit the Gaussians within each cluster using different tiny MLPs, based on importance scores of Gaussians as fitting weights. We experiment on multiple datasets, achieving a 91$\times$ average model size reduction without harming the visual quality.

3D facial avatar reconstruction is a fundamental problem in computer vision and graphics with applications in digital humans, virtual reality, and telepresence. Recent neural radiance field (NeRF)-based methods have greatly improved fidelity, yet most remain subject-specific, requiring multi-view images with diverse expressions and extensive test-time finetuning, which limits their generalization to unseen identities. Achieving high-quality reconstruction from a single image is particularly challenging due to missing multi-view supervision and the need to balance efficiency with fidelity. To address these issues, we present NOFA++, a generalizable one-shot framework that reconstructs photorealistic 3D facial avatars from a single input. Our method leverages the generative prior of a pretrained 3D GAN in an encoder–generator pipeline to recover a canonical neural volume, and introduces a coarse-to-fine residual generation strategy to synthesize identity-specific details without per-subject optimization. We further design a deformation field conditioned on identity and expression parameters to model facial dynamics, enabling controllable reenactment from video or audio. Extensive experiments show that NOFA++ surpasses state-of-the-art baselines in both reconstruction fidelity and reenactment quality, while eliminating test-time finetuning and generalizing robustly across unseen subjects.

3D scene generation is in high demand across various domains, including virtual reality, gaming, and the film industry. Owing to the powerful generative capabilities of text-to-image diffusion models that provide reliable priors, creating 3D scenes using only text prompts has become viable, thereby significantly advancing research in text-driven 3D scene generation. Prevailing methods typically employ the diffusion model to generate an initial local image, followed by iteratively outpainting the local image to gradually generate scenes. Nevertheless, these outpainting-based approaches are prone to producing globally inconsistent results with low completeness, restricting their broader applications. To tackle these problems, we introduce HoloDreamer, a framework that begins by generating a high-definition panorama to holistically initialize the full scene, and leverages 3D Gaussian Splatting (3D-GS) for rapid 3D scene reconstruction, thereby facilitating the creation of view-consistent and fully enclosed 3D scenes. Specifically, we propose Stylized Equirectangular Panorama Generation, a pipeline that combines multiple diffusion models to enable stylized and detailed equirectangular panorama generation from complex text prompts. Subsequently, Enhanced Two-Stage Panorama Reconstruction is introduced, conducting a two-stage optimization of 3D-GS to inpaint the missing region and enhance the integrity of the scene. Comprehensive experiments demonstrated that our method outperforms prior works in terms of overall visual consistency and harmony, as well as reconstruction quality and rendering robustness when generating fully enclosed scenes.

Compared to frame-based methods, computational neuromorphic imaging using event cameras offers significant advantages, such as minimal motion blur, enhanced temporal resolution, and high dynamic range. The multi-view consistency of Neural Radiance Fields combined with the unique benefits of event cameras, has spurred recent research into reconstructing NeRF from data captured by moving event cameras. While showing impressive performance, existing methods rely on ideal conditions with the availability of uniform and high-quality event sequences and accurate camera poses, and mainly focus on the object level reconstruction, thus limiting their practical applications. In this work, we propose AE-NeRF to address the challenges of learning event-based NeRF from non-ideal conditions, including non-uniform event sequences, noisy poses, and various scales of scenes. Our method exploits the density of event streams and jointly learn a pose correction module with an event-based NeRF (e-NeRF) framework for robust 3D reconstruction from inaccurate camera poses. To generalize to larger scenes, we propose hierarchical event distillation with a proposal e-NeRF network and a vanilla e-NeRF network to resample and refine the reconstruction process. We further propose an event reconstruction loss and a temporal loss to improve the view consistency of the reconstructed scene. We established a comprehensive benchmark that includes large-scale scenes to simulate practical non-ideal conditions, incorporating both synthetic and challenging real-world event datasets. The experimental results show that our method achieves a new state-of-the-art in event-based 3D reconstruction.

Recent 3D large reconstruction models typically employ a two-stage process, including first generate multi-view images by a multi-view diffusion model, and then utilize a feed-forward model to reconstruct images to 3D content. However, multi-view diffusion models often produce low-quality and inconsistent images, adversely affecting the quality of the final 3D reconstruction. To address this issue, we propose a unified 3D generation framework called Cycle3D, which cyclically utilizes a 2D diffusion-based generation module and a feed-forward 3D reconstruction module during the multi-step diffusion process. Concretely, 2D diffusion model is applied for generating high-quality texture, and the reconstruction model guarantees multi-view consistency. Moreover, 2D diffusion model can further control the generated content and inject reference-view information for unseen views, thereby enhancing the diversity and texture consistency of 3D generation during the denoising process. Extensive experiments demonstrate the superior ability of our method to create 3D content with high-quality and consistency compared with state-of-the-art baselines.

Indoor scene texture synthesis has garnered significant interest due to its important potential applications in virtual reality, digital media and creative arts. Existing diffusion-model-based researches either rely on per-view inpainting techniques, which are plagued by severe cross-view inconsistencies and conspicuous seams, or adopt optimization-based approaches that involve substantial computational overhead. In this work, we present RoomPainter, a frame-work that seamlessly integrates efficiency and consistency to achieve high-fidelity texturing of indoor scenes. The core of RoomPainter features a zero-shot technique that effectively adapts a 2D diffusion model for 3D-consistent texture synthesis, along with a two-stage generation strategy that ensures both global and local consistency. Specifically, we introduce Attention-Guided Multi-View Integrated Sampling (MVIS) combined with a neighbor-integrated attention mechanism for zero-shot texture map generation. Using the MVIS, we firstly generate texture map for the entire room to ensure global consistency, then adopt its variant, namely Attention-Guided Multi-View Integrated Repaint Sampling (MVRS) to repaint individual instances within the room, thereby further enhancing local consistency and addressing the occlusion problem. Experiments demonstrate that RoomPainter achieves superior performance for indoor scene texture synthesis in visual quality, global consistency and generation efficiency.

Novel view synthesis and 4D reconstruction techniques predominantly rely on RGB cameras, thereby inheriting inherent limitations such as the dependence on adequate lighting, susceptibility to motion blur, and a limited dynamic range. Event cameras, offering advantages of low power, high temporal resolution and high dynamic range, have brought a new perspective to addressing the scene reconstruction challenges in high-speed motion and low-light scenes. To this end, we propose E-4DGS, the first event-driven dynamic Gaussian Splatting approach, for novel view synthesis from multi-view event streams with fast-moving cameras. Specifically, we introduce an event-based initialization scheme to ensure stable training and propose event-adaptive slicing splatting for time-aware reconstruction. Additionally, we employ intensity importance pruning to eliminate floating artifacts and enhance 3D consistency, while incorporating an adaptive contrast threshold for more precise optimization. We design a synthetic multi-view camera setup with six moving event cameras surrounding the object in a 360-degree configuration and provide a benchmark multi-view event stream dataset that captures challenging motion scenarios. Our approach outperforms both event-only and event-RGB fusion baselines and paves the way for the exploration of multi-view event-based reconstruction as a novel approach for rapid scene capture.

We introduce GS2E (Gaussian Splatting to Event Generation), a large-scale synthetic event dataset designed for high-fidelity event vision tasks, captured from real-world sparse multi-view RGB images. Existing event datasets are often synthesized from dense RGB videos, which typically suffer from limited viewpoint diversity and geometric inconsistency, or rely on expensive, hard-to-scale hardware setups. GS2E addresses these limitations by first reconstructing photorealistic static scenes using 3D Gaussian Splatting, followed by a novel, physically-informed event simulation pipeline. This pipeline integrates adaptive trajectory interpolation with physically-consistent event contrast threshold modeling. As a result, it generates temporally dense and geometrically consistent event streams under diverse motion and lighting conditions, while maintaining strong alignment with the underlying scene structure. Experimental results on event-based 3D reconstruction highlight GS2E’s superior generalization capabilities and its practical value as a benchmark for advancing event vision research.

Traditional feature-based image stitching techniques rely heavily on the quality of feature detection and often fail to get a high quality solution for images with fewer features. Generating high-quality stitching images with a natural structure is still a challenging task in computer vision. The current distortion-based image alignment relies on the division of the grid, which is currently mostly equally divided without reference to the information in the image itself, and thus there are some problems such as straight line retention in the alignment stage. On this basis, if the deep learning approach is added in the later reconstruction stage to limit the generation of artifacts at the pixel level, it will be greatly improved, and we can ensure the high quality of the final splicing result of the image through two stages. In this paper, we succeed in proposing a novelty model called multi-scale image stitching based on unsupervised controllable fusion module which can be divided in two stages: Multi-scale grids alignment structure based on feature points density and image reconstruction structure based on unsupervised controllable fusion structure. We develop new energy terms to adapt to limit the transformations of the new grids. Extensive experiments demonstrate that the proposed method outperforms most state-of-the-arts by effectively preserving the linear structure in the image and improving the robustness.

Face photo-sketch synthesis tasks have been dominated by convolutional neural networks (CNNs), especially CNN-based generative adversarial networks (GANs), because of their strong texture modeling capabilities and thus their ability to generate more realistic face photos/sketches beyond traditional methods. However, due to CNNs' locality and spatial invariance properties, there have weaknesses in capturing the global and structural information which are extremely important for face images. Inspired by the recent phenomenal success of the Transformer in vision tasks, we propose replacing CNNs with Transformers that are able to model long-range dependencies to synthesize more structured and realistic face images. However, the existing vision Transformers are mainly designed for high-level vision tasks and lack the dense prediction ability to generate high resolution images due to the quadratic computational complexity of their self-attention mechanism. In addition, the original Transformer is not capable of modeling local correlations which is an important skill for image generation. To address these challenges, we propose two types of memory-friendly Transformer encoders, one for processing local correlations via local self-attention and another for modeling global information via global self-attention. By integrating the two proposed Transformer encoders, we present an efficient GL-Transformer for face photo-sketch synthesis, which can synthesize realistic face photo/sketch images from coarse to fine. Extensive experiments demonstrate that our model achieves a comparable or better performance beyond the state-of-the-art CNN-based methods both qualitatively and quantitatively.

Image inpainting approaches have achieved significant progress with the help of deep neural networks. How-ever, existing approaches mainly focus on leveraging the priori distribution learned by neural networks to produce a single inpainting result or further yielding multiple solutions, where the controllability is not well studied. This paper develops a novel image inpainting approach that enables users to customize the inpainting result by their own preference or memory. Specifically, our approach is composed of two stages that utilize the prior of neural network and user’s guidance to jointly inpaint corrupted images. In the first stage, an autoencoder based on a novel external spatial attention mechanism is deployed to produce reconstructed features of the corrupted image and a coarse inpainting result that provides semantic mask as the medium for user interaction. In the second stage, a semantic decoder that takes the reconstructed features as prior is adopted to synthesize a fine inpainting result guided by user’s customized semantic mask, so that the final inpainting result will share the same content with user’s guidance while the textures and colors reconstructed in the first stage are preserved. Extensive experiments demonstrate the superiority of our approach in terms of inpainting quality and controllability.