Unified Semantic Transformer for 3D Scene Understanding

Holistic 3D scene understanding involves capturing and parsing unstructured 3D environments. Due to the inherent complexity of the real world, existing models have predominantly been developed and limited to be task-specific. We introduce UNITE, a Unified Semantic Transformer for 3D scene understanding, a novel feed-forward neural network that unifies a diverse set of 3D semantic tasks within a single model. Our model operates on unseen scenes in a fully end-to-end manner and only takes a few seconds to infer the full 3D semantic geometry. Our approach is capable of directly predicting multiple semantic attributes, including 3D scene segmentation, instance embeddings, open-vocabulary features, as well as affordance and articulations, solely from RGB images. The method is trained using a combination of 2D distillation, heavily relying on self-supervision and leverages novel multi-view losses designed to ensure 3D view consistency. We demonstrate that UNITE achieves state-of-the-art performance on several different semantic tasks and even outperforms task-specific models, in many cases, surpassing methods that operate on ground truth 3D geometry. See the project website at unite-page.github.io

Elastic3D: Controllable Stereo Video Conversion with Guided Latent Decoding

The growing demand for immersive 3D content calls for automated monocular-to-stereo video conversion. We present Elastic3D, a controllable, direct end-to-end method for upgrading a conventional video to a binocular one. Our approach, based on (conditional) latent diffusion, avoids artifacts due to explicit depth estimation and warping. The key to its high-quality stereo video output is a novel, guided VAE decoder that ensures sharp and epipolar-consistent stereo video output. Moreover, our method gives the user control over the strength of the stereo effect (more precisely, the disparity range) at inference time, via an intuitive, scalar tuning knob. Experiments on three different datasets of real-world stereo videos show that our method outperforms both traditional warping-based and recent warping-free baselines and sets a new standard for reliable, controllable stereo video conversion. Please check the project page for the video samples https://elastic3d.github.io.

Epipolar Geometry Improves Video Generation Models

Video generation models have progressed tremendously through large latent diffusion transformers trained with rectified flow techniques. Yet these models still struggle with geometric inconsistencies, unstable motion, and visual artifacts that break the illusion of realistic 3D scenes. 3D-consistent video generation could significantly impact numerous downstream applications in generation and reconstruction tasks. We explore how epipolar geometry constraints improve modern video diffusion models. Despite massive training data, these models fail to capture fundamental geometric principles underlying visual content. We align diffusion models using pairwise epipolar geometry constraints via preference-based optimization, directly addressing unstable camera trajectories and geometric artifacts through mathematically principled geometric enforcement. Our approach efficiently enforces geometric principles without requiring end-to-end differentiability. Evaluation demonstrates that classical geometric constraints provide more stable optimization signals than modern learned metrics, which produce noisy targets that compromise alignment quality. Training on static scenes with dynamic cameras ensures high-quality measurements while the model generalizes effectively to diverse dynamic content. By bridging data-driven deep learning with classical geometric computer vision, we present a practical method for generating spatially consistent videos without compromising visual quality.

AnyUp: Universal Feature Upsampling

We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. Existing learning-based upsamplers for features like DINO or CLIP need to be re-trained for every feature extractor and thus do not generalize to different feature types at inference time. In this work, we propose an inference-time feature-agnostic upsampling architecture to alleviate this limitation and improve upsampling quality. In our experiments, AnyUp sets a new state of the art for upsampled features, generalizes to different feature types, and preserves feature semantics while being efficient and easy to apply to a wide range of downstream tasks.

RefAM: Attention Magnets for Zero-Shot Referral Segmentation

Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models, often at the cost of additional training and architectural modifications. Meanwhile, large-scale generative diffusion models encode rich semantic information, making them attractive as general-purpose feature extractors. In this work, we introduce a new method that directly exploits features, attention scores, from diffusion transformers for downstream tasks, requiring neither architectural modifications nor additional training. To systematically evaluate these features, we extend benchmarks with vision-language grounding tasks spanning both images and videos. Our key insight is that stop words act as attention magnets: they accumulate surplus attention and can be filtered to reduce noise. Moreover, we identify global attention sinks (GAS) emerging in deeper layers and show that they can be safely suppressed or redirected onto auxiliary tokens, leading to sharper and more accurate grounding maps. We further propose an attention redistribution strategy, where appended stop words partition background activations into smaller clusters, yielding sharper and more localized heatmaps. Building on these findings, we develop RefAM, a simple training-free grounding framework that combines cross-attention maps, GAS handling, and redistribution. Across zero-shot referring image and video segmentation benchmarks, our approach consistently outperforms prior methods, establishing a new state of the art without fine-tuning or additional components.

Lost in Translation? Vocabulary Alignment for Source-Free Domain Adaptation in Open-Vocabulary Semantic Segmentation

We introduce VocAlign, a novel source-free domain adaptation framework specifically designed for VLMs in open-vocabulary semantic segmentation. Our method adopts a student-teacher paradigm enhanced with a vocabulary alignment strategy, which improves pseudo-label generation by incorporating additional class concepts. To ensure efficiency, we use Low-Rank Adaptation (LoRA) to fine-tune the model, preserving its original capabilities while minimizing computational overhead. In addition, we propose a Top-K class selection mechanism for the student model, which significantly reduces memory requirements while further improving adaptation performance. Our approach achieves a notable 6.11 mIoU improvement on the CityScapes dataset and demonstrates superior performance on zero-shot segmentation benchmarks, setting a new standard for source-free adaptation in the open-vocabulary setting.

GALA: Guided Attention with Language Alignment for Open Vocabulary Gaussian Splatting

3D scene reconstruction and understanding have gained increasing popularity, yet existing methods still struggle to capture fine-grained, language-aware 3D representations from 2D images. In this paper, we present GALA, a novel framework for open-vocabulary 3D scene understanding with 3D Gaussian Splatting (3DGS). GALA distills a scene-specific 3D instance feature field via self-supervised contrastive learning. To extend to generalized language feature fields, we introduce the core contribution of GALA, a cross-attention module with two learnable codebooks that encode view-independent semantic embeddings. This design not only ensures intra-instance feature similarity but also supports seamless 2D and 3D open-vocabulary queries. It reduces memory consumption by avoiding per-Gaussian high-dimensional feature learning. Extensive experiments on real-world datasets demonstrate GALA's remarkable open-vocabulary performance on both 2D and 3D.

Masks make discriminative models great again!

We present Image2GS, a novel approach that addresses the challenging problem of reconstructing photorealistic 3D scenes from a single image by focusing specifically on the image-to-3D lifting component of the reconstruction process. By decoupling the lifting problem (converting an image to a 3D model representing what is visible) from the completion problem (hallucinating content not present in the input), we create a more deterministic task suitable for discriminative models. Our method employs visibility masks derived from optimized 3D Gaussian splats to exclude areas not visible from the source view during training. This masked training strategy significantly improves reconstruction quality in visible regions compared to strong baselines. Notably, despite being trained only on masked regions, Image2GS remains competitive with state-of-the-art discriminative models trained on full target images when evaluated on complete scenes. Our findings highlight the fundamental struggle discriminative models face when fitting unseen regions and demonstrate the advantages of addressing image-to-3D lifting as a distinct problem with specialized techniques.

Video Perception Models for 3D Scene Synthesis

Traditionally, 3D scene synthesis requires expert knowledge and significant manual effort. Automating this process could greatly benefit fields such as architectural design, robotics simulation, virtual reality, and gaming. Recent approaches to 3D scene synthesis often rely on the commonsense reasoning of large language models (LLMs) or strong visual priors of modern image generation models. However, current LLMs demonstrate limited 3D spatial reasoning ability, which restricts their ability to generate realistic and coherent 3D scenes. Meanwhile, image generation-based methods often suffer from constraints in viewpoint selection and multi-view inconsistencies. In this work, we present Video Perception models for 3D Scene synthesis (VIPScene), a novel framework that exploits the encoded commonsense knowledge of the 3D physical world in video generation models to ensure coherent scene layouts and consistent object placements across views. VIPScene accepts both text and image prompts and seamlessly integrates video generation, feedforward 3D reconstruction, and open-vocabulary perception models to semantically and geometrically analyze each object in a scene. This enables flexible scene synthesis with high realism and structural consistency. For more precise analysis, we further introduce First-Person View Score (FPVScore) for coherence and plausibility evaluation, utilizing continuous first-person perspective to capitalize on the reasoning ability of multimodal large language models. Extensive experiments show that VIPScene significantly outperforms existing methods and generalizes well across diverse scenarios. The code will be released.

Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations

Learning effective multi-modal 3D representations of objects is essential for numerous applications, such as augmented reality and robotics. Existing methods often rely on task-specific embeddings that are tailored either for semantic understanding or geometric reconstruction. As a result, these embeddings typically cannot be decoded into explicit geometry and simultaneously reused across tasks. In this paper, we propose Object-X, a versatile multi-modal object representation framework capable of encoding rich object embeddings (e.g. images, point cloud, text) and decoding them back into detailed geometric and visual reconstructions. Object-X operates by geometrically grounding the captured modalities in a 3D voxel grid and learning an unstructured embedding fusing the information from the voxels with the object attributes. The learned embedding enables 3D Gaussian Splatting-based object reconstruction, while also supporting a range of downstream tasks, including scene alignment, single-image 3D object reconstruction, and localization. Evaluations on two challenging real-world datasets demonstrate that Object-X produces high-fidelity novel-view synthesis comparable to standard 3D Gaussian Splatting, while significantly improving geometric accuracy. Moreover, Object-X achieves competitive performance with specialized methods in scene alignment and localization. Critically, our object-centric descriptors require 3-4 orders of magnitude less storage compared to traditional image- or point cloud-based approaches, establishing Object-X as a scalable and highly practical solution for multi-modal 3D scene representation.