Peter Wonka

Shariq Farooq Bhat, Reiner Birkl, Diana Wofk et al.

This paper tackles the problem of depth estimation from a single image. Existing work either focuses on generalization performance disregarding metric scale, i.e. relative depth estimation, or state-of-the-art results on specific datasets, i.e. metric depth estimation. We propose the first approach that combines both worlds, leading to a model with excellent generalization performance while maintaining metric scale. Our flagship model, ZoeD-M12-NK, is pre-trained on 12 datasets using relative depth and fine-tuned on two datasets using metric depth. We use a lightweight head with a novel bin adjustment design called metric bins module for each domain. During inference, each input image is automatically routed to the appropriate head using a latent classifier. Our framework admits multiple configurations depending on the datasets used for relative depth pre-training and metric fine-tuning. Without pre-training, we can already significantly improve the state of the art (SOTA) on the NYU Depth v2 indoor dataset. Pre-training on twelve datasets and fine-tuning on the NYU Depth v2 indoor dataset, we can further improve SOTA for a total of 21% in terms of relative absolute error (REL). Finally, ZoeD-M12-NK is the first model that can jointly train on multiple datasets (NYU Depth v2 and KITTI) without a significant drop in performance and achieve unprecedented zero-shot generalization performance to eight unseen datasets from both indoor and outdoor domains. The code and pre-trained models are publicly available at https://github.com/isl-org/ZoeDepth .

Guocheng Qian, Jinjie Mai, Abdullah Hamdi et al.

We present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter between the 2D and 3D priors to control exploration (more imaginative) and exploitation (more precise) of the generated geometry. Additionally, we employ textual inversion and monocular depth regularization to encourage consistent appearances across views and to prevent degenerate solutions, respectively. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on synthetic benchmarks and diverse real-world images. Our code, models, and generated 3D assets are available at https://github.com/guochengqian/Magic123.

Yiqun Wang, Ivan Skorokhodov, Peter Wonka

Neural rendering can be used to reconstruct implicit representations of shapes without 3D supervision. However, current neural surface reconstruction methods have difficulty learning high-frequency geometry details, so the reconstructed shapes are often over-smoothed. We develop HF-NeuS, a novel method to improve the quality of surface reconstruction in neural rendering. We follow recent work to model surfaces as signed distance functions (SDFs). First, we offer a derivation to analyze the relationship between the SDF, the volume density, the transparency function, and the weighting function used in the volume rendering equation and propose to model transparency as transformed SDF. Second, we observe that attempting to jointly encode high-frequency and low-frequency components in a single SDF leads to unstable optimization. We propose to decompose the SDF into a base function and a displacement function with a coarse-to-fine strategy to gradually increase the high-frequency details. Finally, we design an adaptive optimization strategy that makes the training process focus on improving those regions near the surface where the SDFs have artifacts. Our qualitative and quantitative results show that our method can reconstruct fine-grained surface details and obtain better surface reconstruction quality than the current state of the art. Code available at https://github.com/yiqun-wang/HFS.

Sherwin Bahmani, Ivan Skorokhodov, Victor Rong et al. · stanford

Recent breakthroughs in text-to-4D generation rely on pre-trained text-to-image and text-to-video models to generate dynamic 3D scenes. However, current text-to-4D methods face a three-way tradeoff between the quality of scene appearance, 3D structure, and motion. For example, text-to-image models and their 3D-aware variants are trained on internet-scale image datasets and can be used to produce scenes with realistic appearance and 3D structure -- but no motion. Text-to-video models are trained on relatively smaller video datasets and can produce scenes with motion, but poorer appearance and 3D structure. While these models have complementary strengths, they also have opposing weaknesses, making it difficult to combine them in a way that alleviates this three-way tradeoff. Here, we introduce hybrid score distillation sampling, an alternating optimization procedure that blends supervision signals from multiple pre-trained diffusion models and incorporates benefits of each for high-fidelity text-to-4D generation. Using hybrid SDS, we demonstrate synthesis of 4D scenes with compelling appearance, 3D structure, and motion.

Anna Frühstück, Nikolaos Sarafianos, Yuanlu Xu et al. · meta-ai

We introduce VIVE3D, a novel approach that extends the capabilities of image-based 3D GANs to video editing and is able to represent the input video in an identity-preserving and temporally consistent way. We propose two new building blocks. First, we introduce a novel GAN inversion technique specifically tailored to 3D GANs by jointly embedding multiple frames and optimizing for the camera parameters. Second, besides traditional semantic face edits (e.g. for age and expression), we are the first to demonstrate edits that show novel views of the head enabled by the inherent properties of 3D GANs and our optical flow-guided compositing technique to combine the head with the background video. Our experiments demonstrate that VIVE3D generates high-fidelity face edits at consistent quality from a range of camera viewpoints which are composited with the original video in a temporally and spatially consistent manner.

Yicheng Luo, Jing Ren, Xuefei Zhe et al.

Line clouds, though under-investigated in the previous work, potentially encode more compact structural information of buildings than point clouds extracted from multi-view images. In this work, we propose the first network to process line clouds for building wireframe abstraction. The network takes a line cloud as input , i.e., a nonstructural and unordered set of 3D line segments extracted from multi-view images, and outputs a 3D wireframe of the underlying building, which consists of a sparse set of 3D junctions connected by line segments. We observe that a line patch, i.e., a group of neighboring line segments, encodes sufficient contour information to predict the existence and even the 3D position of a potential junction, as well as the likelihood of connectivity between two query junctions. We therefore introduce a two-layer Line-Patch Transformer to extract junctions and connectivities from sampled line patches to form a 3D building wireframe model. We also introduce a synthetic dataset of multi-view images with ground-truth 3D wireframe. We extensively justify that our reconstructed 3D wireframe models significantly improve upon multiple baseline building reconstruction methods. The code and data can be found at https://github.com/Luo1Cheng/LC2WF.

Biao Zhang, Jiapeng Tang, Matthias Niessner et al.

We introduce 3DShape2VecSet, a novel shape representation for neural fields designed for generative diffusion models. Our shape representation can encode 3D shapes given as surface models or point clouds, and represents them as neural fields. The concept of neural fields has previously been combined with a global latent vector, a regular grid of latent vectors, or an irregular grid of latent vectors. Our new representation encodes neural fields on top of a set of vectors. We draw from multiple concepts, such as the radial basis function representation and the cross attention and self-attention function, to design a learnable representation that is especially suitable for processing with transformers. Our results show improved performance in 3D shape encoding and 3D shape generative modeling tasks. We demonstrate a wide variety of generative applications: unconditioned generation, category-conditioned generation, text-conditioned generation, point-cloud completion, and image-conditioned generation.

Ryan Po, Wang Yifan, Vladislav Golyanik et al.

The field of visual computing is rapidly advancing due to the emergence of generative artificial intelligence (AI), which unlocks unprecedented capabilities for the generation, editing, and reconstruction of images, videos, and 3D scenes. In these domains, diffusion models are the generative AI architecture of choice. Within the last year alone, the literature on diffusion-based tools and applications has seen exponential growth and relevant papers are published across the computer graphics, computer vision, and AI communities with new works appearing daily on arXiv. This rapid growth of the field makes it difficult to keep up with all recent developments. The goal of this state-of-the-art report (STAR) is to introduce the basic mathematical concepts of diffusion models, implementation details and design choices of the popular Stable Diffusion model, as well as overview important aspects of these generative AI tools, including personalization, conditioning, inversion, among others. Moreover, we give a comprehensive overview of the rapidly growing literature on diffusion-based generation and editing, categorized by the type of generated medium, including 2D images, videos, 3D objects, locomotion, and 4D scenes. Finally, we discuss available datasets, metrics, open challenges, and social implications. This STAR provides an intuitive starting point to explore this exciting topic for researchers, artists, and practitioners alike.

Thomas Wimmer, Peter Wonka, Maks Ovsjanikov · eth-zurich

With the immense growth of dataset sizes and computing resources in recent years, so-called foundation models have become popular in NLP and vision tasks. In this work, we propose to explore foundation models for the task of keypoint detection on 3D shapes. A unique characteristic of keypoint detection is that it requires semantic and geometric awareness while demanding high localization accuracy. To address this problem, we propose, first, to back-project features from large pre-trained 2D vision models onto 3D shapes and employ them for this task. We show that we obtain robust 3D features that contain rich semantic information and analyze multiple candidate features stemming from different 2D foundation models. Second, we employ a keypoint candidate optimization module which aims to match the average observed distribution of keypoints on the shape and is guided by the back-projected features. The resulting approach achieves a new state of the art for few-shot keypoint detection on the KeyPointNet dataset, almost doubling the performance of the previous best methods.

Biao Zhang, Matthias Nießner, Peter Wonka

We propose a new representation for encoding 3D shapes as neural fields. The representation is designed to be compatible with the transformer architecture and to benefit both shape reconstruction and shape generation. Existing works on neural fields are grid-based representations with latents defined on a regular grid. In contrast, we define latents on irregular grids, enabling our representation to be sparse and adaptive. In the context of shape reconstruction from point clouds, our shape representation built on irregular grids improves upon grid-based methods in terms of reconstruction accuracy. For shape generation, our representation promotes high-quality shape generation using auto-regressive probabilistic models. We show different applications that improve over the current state of the art. First, we show results for probabilistic shape reconstruction from a single higher resolution image. Second, we train a probabilistic model conditioned on very low resolution images. Third, we apply our model to category-conditioned generation. All probabilistic experiments confirm that we are able to generate detailed and high quality shapes to yield the new state of the art in generative 3D shape modeling.

Shariq Farooq Bhat, Ibraheem Alhashim, Peter Wonka

We propose a novel architecture for depth estimation from a single image. The architecture itself is based on the popular encoder-decoder architecture that is frequently used as a starting point for all dense regression tasks. We build on AdaBins which estimates a global distribution of depth values for the input image and evolve the architecture in two ways. First, instead of predicting global depth distributions, we predict depth distributions of local neighborhoods at every pixel. Second, instead of predicting depth distributions only towards the end of the decoder, we involve all layers of the decoder. We call this new architecture LocalBins. Our results demonstrate a clear improvement over the state-of-the-art in all metrics on the NYU-Depth V2 dataset. Code and pretrained models will be made publicly available.

Ivan Skorokhodov, Sergey Tulyakov, Yiqun Wang et al.

A very recent trend in generative modeling is building 3D-aware generators from 2D image collections. To induce the 3D bias, such models typically rely on volumetric rendering, which is expensive to employ at high resolutions. During the past months, there appeared more than 10 works that address this scaling issue by training a separate 2D decoder to upsample a low-resolution image (or a feature tensor) produced from a pure 3D generator. But this solution comes at a cost: not only does it break multi-view consistency (i.e. shape and texture change when the camera moves), but it also learns the geometry in a low fidelity. In this work, we show that it is possible to obtain a high-resolution 3D generator with SotA image quality by following a completely different route of simply training the model patch-wise. We revisit and improve this optimization scheme in two ways. First, we design a location- and scale-aware discriminator to work on patches of different proportions and spatial positions. Second, we modify the patch sampling strategy based on an annealed beta distribution to stabilize training and accelerate the convergence. The resulted model, named EpiGRAF, is an efficient, high-resolution, pure 3D generator, and we test it on four datasets (two introduced in this work) at $256^2$ and $512^2$ resolutions. It obtains state-of-the-art image quality, high-fidelity geometry and trains ${\approx} 2.5 \times$ faster than the upsampler-based counterparts. Project website: https://universome.github.io/epigraf.

Jian Shi, Pengyi Zhang, Ni Zhang et al.

Medical imaging often contains critical fine-grained features, such as tumors or hemorrhages, crucial for diagnosis yet potentially too subtle for detection with conventional methods. In this paper, we introduce \textit{DIA}, dissolving is amplifying. DIA is a fine-grained anomaly detection framework for medical images. First, we introduce \textit{dissolving transformations}. We employ diffusion with a generative diffusion model as a dedicated feature-aware denoiser. Applying diffusion to medical images in a certain manner can remove or diminish fine-grained discriminative features. Second, we introduce an \textit{amplifying framework} based on contrastive learning to learn a semantically meaningful representation of medical images in a self-supervised manner, with a focus on fine-grained features. The amplifying framework contrasts additional pairs of images with and without dissolving transformations applied and thereby emphasizes the dissolved fine-grained features. DIA significantly improves the medical anomaly detection performance with around 18.40\% AUC boost against the baseline method and achieves an overall SOTA against other benchmark methods. Our code is available at \url{https://github.com/shijianjian/DIA.git}.

Anna Frühstück, Krishna Kumar Singh, Eli Shechtman et al.

While GANs can produce photo-realistic images in ideal conditions for certain domains, the generation of full-body human images remains difficult due to the diversity of identities, hairstyles, clothing, and the variance in pose. Instead of modeling this complex domain with a single GAN, we propose a novel method to combine multiple pretrained GANs, where one GAN generates a global canvas (e.g., human body) and a set of specialized GANs, or insets, focus on different parts (e.g., faces, shoes) that can be seamlessly inserted onto the global canvas. We model the problem as jointly exploring the respective latent spaces such that the generated images can be combined, by inserting the parts from the specialized generators onto the global canvas, without introducing seams. We demonstrate the setup by combining a full body GAN with a dedicated high-quality face GAN to produce plausible-looking humans. We evaluate our results with quantitative metrics and user studies.

Ahmed Abdelreheem, Ivan Skorokhodov, Maks Ovsjanikov et al.

We explore the task of zero-shot semantic segmentation of 3D shapes by using large-scale off-the-shelf 2D image recognition models. Surprisingly, we find that modern zero-shot 2D object detectors are better suited for this task than contemporary text/image similarity predictors or even zero-shot 2D segmentation networks. Our key finding is that it is possible to extract accurate 3D segmentation maps from multi-view bounding box predictions by using the topological properties of the underlying surface. For this, we develop the Segmentation Assignment with Topological Reweighting (SATR) algorithm and evaluate it on ShapeNetPart and our proposed FAUST benchmarks. SATR achieves state-of-the-art performance and outperforms a baseline algorithm by 1.3% and 4% average mIoU on the FAUST coarse and fine-grained benchmarks, respectively, and by 5.2% average mIoU on the ShapeNetPart benchmark. Our source code and data will be publicly released. Project webpage: https://samir55.github.io/SATR/.

Ivan Skorokhodov, Aliaksandr Siarohin, Yinghao Xu et al.

Existing 3D-from-2D generators are typically designed for well-curated single-category datasets, where all the objects have (approximately) the same scale, 3D location, and orientation, and the camera always points to the center of the scene. This makes them inapplicable to diverse, in-the-wild datasets of non-alignable scenes rendered from arbitrary camera poses. In this work, we develop a 3D generator with Generic Priors (3DGP): a 3D synthesis framework with more general assumptions about the training data, and show that it scales to very challenging datasets, like ImageNet. Our model is based on three new ideas. First, we incorporate an inaccurate off-the-shelf depth estimator into 3D GAN training via a special depth adaptation module to handle the imprecision. Then, we create a flexible camera model and a regularization strategy for it to learn its distribution parameters during training. Finally, we extend the recent ideas of transferring knowledge from pre-trained classifiers into GANs for patch-wise trained models by employing a simple distillation-based technique on top of the discriminator. It achieves more stable training than the existing methods and speeds up the convergence by at least 40%. We explore our model on four datasets: SDIP Dogs 256x256, SDIP Elephants 256x256, LSUN Horses 256x256, and ImageNet 256x256, and demonstrate that 3DGP outperforms the recent state-of-the-art in terms of both texture and geometry quality. Code and visualizations: https://snap-research.github.io/3dgp.

Rameen Abdal, Hsin-Ying Lee, Peihao Zhu et al.

Modern 3D-GANs synthesize geometry and texture by training on large-scale datasets with a consistent structure. Training such models on stylized, artistic data, with often unknown, highly variable geometry, and camera information has not yet been shown possible. Can we train a 3D GAN on such artistic data, while maintaining multi-view consistency and texture quality? To this end, we propose an adaptation framework, where the source domain is a pre-trained 3D-GAN, while the target domain is a 2D-GAN trained on artistic datasets. We then distill the knowledge from a 2D generator to the source 3D generator. To do that, we first propose an optimization-based method to align the distributions of camera parameters across domains. Second, we propose regularizations necessary to learn high-quality texture, while avoiding degenerate geometric solutions, such as flat shapes. Third, we show a deformation-based technique for modeling exaggerated geometry of artistic domains, enabling -- as a byproduct -- personalized geometric editing. Finally, we propose a novel inversion method for 3D-GANs linking the latent spaces of the source and the target domains. Our contributions -- for the first time -- allow for the generation, editing, and animation of personalized artistic 3D avatars on artistic datasets.

Ahmed Abdelreheem, Abdelrahman Eldesokey, Maks Ovsjanikov et al.

We propose a novel zero-shot approach to computing correspondences between 3D shapes. Existing approaches mainly focus on isometric and near-isometric shape pairs (e.g., human vs. human), but less attention has been given to strongly non-isometric and inter-class shape matching (e.g., human vs. cow). To this end, we introduce a fully automatic method that exploits the exceptional reasoning capabilities of recent foundation models in language and vision to tackle difficult shape correspondence problems. Our approach comprises multiple stages. First, we classify the 3D shapes in a zero-shot manner by feeding rendered shape views to a language-vision model (e.g., BLIP2) to generate a list of class proposals per shape. These proposals are unified into a single class per shape by employing the reasoning capabilities of ChatGPT. Second, we attempt to segment the two shapes in a zero-shot manner, but in contrast to the co-segmentation problem, we do not require a mutual set of semantic regions. Instead, we propose to exploit the in-context learning capabilities of ChatGPT to generate two different sets of semantic regions for each shape and a semantic mapping between them. This enables our approach to match strongly non-isometric shapes with significant differences in geometric structure. Finally, we employ the generated semantic mapping to produce coarse correspondences that can further be refined by the functional maps framework to produce dense point-to-point maps. Our approach, despite its simplicity, produces highly plausible results in a zero-shot manner, especially between strongly non-isometric shapes. Project webpage: https://samir55.github.io/3dshapematch/.

Ahmed Abdelreheem, Kyle Olszewski, Hsin-Ying Lee et al.

The two popular datasets ScanRefer [16] and ReferIt3D [3] connect natural language to real-world 3D data. In this paper, we curate a large-scale and complementary dataset extending both the aforementioned ones by associating all objects mentioned in a referential sentence to their underlying instances inside a 3D scene. Specifically, our Scan Entities in 3D (ScanEnts3D) dataset provides explicit correspondences between 369k objects across 84k natural referential sentences, covering 705 real-world scenes. Crucially, we show that by incorporating intuitive losses that enable learning from this novel dataset, we can significantly improve the performance of several recently introduced neural listening architectures, including improving the SoTA in both the Nr3D and ScanRefer benchmarks by 4.3% and 5.0%, respectively. Moreover, we experiment with competitive baselines and recent methods for the task of language generation and show that, as with neural listeners, 3D neural speakers can also noticeably benefit by training with ScanEnts3D, including improving the SoTA by 13.2 CIDEr points on the Nr3D benchmark. Overall, our carefully conducted experimental studies strongly support the conclusion that, by learning on ScanEnts3D, commonly used visio-linguistic 3D architectures can become more efficient and interpretable in their generalization without needing to provide these newly collected annotations at test time. The project's webpage is https://scanents3d.github.io/ .

Qian Wang, Biao Zhang, Michael Birsak et al.

Image generation using diffusion can be controlled in multiple ways. In this paper, we systematically analyze the equations of modern generative diffusion networks to propose a framework, called MDP, that explains the design space of suitable manipulations. We identify 5 different manipulations, including intermediate latent, conditional embedding, cross attention maps, guidance, and predicted noise. We analyze the corresponding parameters of these manipulations and the manipulation schedule. We show that some previous editing methods fit nicely into our framework. Particularly, we identified one specific configuration as a new type of control by manipulating the predicted noise, which can perform higher-quality edits than previous work for a variety of local and global edits.

Wamiq Reyaz Para, Paul Guerrero, Niloy Mitra et al.

Scalable generation of furniture layouts is essential for many applications in virtual reality, augmented reality, game development and synthetic data generation. Many existing methods tackle this problem as a sequence generation problem which imposes a specific ordering on the elements of the layout making such methods impractical for interactive editing or scene completion. Additionally, most methods focus on generating layouts unconditionally and offer minimal control over the generated layouts. We propose COFS, an architecture based on standard transformer architecture blocks from language modeling. The proposed model is invariant to object order by design, removing the unnatural requirement of specifying an object generation order. Furthermore, the model allows for user interaction at multiple levels enabling fine grained control over the generation process. Our model consistently outperforms other methods which we verify by performing quantitative evaluations. Our method is also faster to train and sample from, compared to existing methods.

Abdalla G. M. Ahmed, Jing Ren, Peter Wonka

Among the various approaches for producing point distributions with blue noise spectrum, we argue for an optimization framework using Gaussian kernels. We show that with a wise selection of optimization parameters, this approach attains unprecedented quality, provably surpassing the current state of the art attained by the optimal transport (BNOT) approach. Further, we show that our algorithm scales smoothly and feasibly to high dimensions while maintaining the same quality, realizing unprecedented high-quality high-dimensional blue noise sets. Finally, we show an extension to adaptive sampling.

Qian Wang, Yiqun Wang, Michael Birsak et al.

3D-aware image synthesis has attracted increasing interest as it models the 3D nature of our real world. However, performing realistic object-level editing of the generated images in the multi-object scenario still remains a challenge. Recently, a 2D GAN termed BlobGAN has demonstrated great multi-object editing capabilities on real-world indoor scene datasets. In this work, we propose BlobGAN-3D, which is a 3D-aware improvement of the original 2D BlobGAN. We enable explicit camera pose control while maintaining the disentanglement for individual objects in the scene by extending the 2D blobs into 3D blobs. We keep the object-level editing capabilities of BlobGAN and in addition allow flexible control over the 3D location of the objects in the scene. We test our method on real-world indoor datasets and show that our method can achieve comparable image quality compared to the 2D BlobGAN and other 3D-aware GAN baselines while being able to enable camera pose control and object-level editing in the challenging multi-object real-world scenarios.

Jheng-Wei Su, Chi-Han Peng, Peter Wonka et al.

Reconstructing 3D layouts from multiple $360^{\circ}$ panoramas has received increasing attention recently as estimating a complete layout of a large-scale and complex room from a single panorama is very difficult. The state-of-the-art method, called PSMNet, introduces the first learning-based framework that jointly estimates the room layout and registration given a pair of panoramas. However, PSMNet relies on an approximate (i.e., "noisy") registration as input. Obtaining this input requires a solution for wide baseline registration which is a challenging problem. In this work, we present a complete multi-view panoramic layout estimation framework that jointly learns panorama registration and layout estimation given a pair of panoramas without relying on a pose prior. The major improvement over PSMNet comes from a novel Geometry-aware Panorama Registration Network or GPR-Net that effectively tackles the wide baseline registration problem by exploiting the layout geometry and computing fine-grained correspondences on the layout boundaries, instead of the global pixel-space. Our architecture consists of two parts. First, given two panoramas, we adopt a vision transformer to learn a set of 1D horizon features sampled on the panorama. These 1D horizon features encode the depths of individual layout boundary samples and the correspondence and covisibility maps between layout boundaries. We then exploit a non-linear registration module to convert these 1D horizon features into a set of corresponding 2D boundary points on the layout. Finally, we estimate the final relative camera pose via RANSAC and obtain the complete layout simply by taking the union of registered layouts. Experimental results indicate that our method achieves state-of-the-art performance in both panorama registration and layout estimation on a large-scale indoor panorama dataset ZInD.

Rameen Abdal, Peihao Zhu, Niloy J. Mitra et al.

Image editing using a pretrained StyleGAN generator has emerged as a powerful paradigm for facial editing, providing disentangled controls over age, expression, illumination, etc. However, the approach cannot be directly adopted for video manipulations. We hypothesize that the main missing ingredient is the lack of fine-grained and disentangled control over face location, face pose, and local facial expressions. In this work, we demonstrate that such a fine-grained control is indeed achievable using pretrained StyleGAN by working across multiple (latent) spaces (namely, the positional space, the W+ space, and the S space) and combining the optimization results across the multiple spaces. Building on this enabling component, we introduce Video2StyleGAN that takes a target image and driving video(s) to reenact the local and global locations and expressions from the driving video in the identity of the target image. We evaluate the effectiveness of our method over multiple challenging scenarios and demonstrate clear improvements over alternative approaches.

Michael Birsak, Tom Kelly, Wamiq Para et al.

We present a novel generative method for the creation of city-scale road layouts. While the output of recent methods is limited in both size of the covered area and diversity, our framework produces large traversable graphs of high quality consisting of vertices and edges representing complete street networks covering 400 square kilometers or more. While our framework can process general 2D embedded graphs, we focus on street networks due to the wide availability of training data. Our generative framework consists of a transformer decoder that is used in a sliding window manner to predict a field of indices, with each index encoding a representation of the local neighborhood. The semantics of each index is determined by a dictionary of context vectors. The index field is then input to a decoder to compute the street graph. Using data from OpenStreetMap, we train our system on whole cities and even across large countries such as the US, and finally compare it to the state of the art.

Azimkhon Ostonov, Peter Wonka, Dominik L. Michels

We present RLSS: a reinforcement learning algorithm for sequential scene generation. This is based on employing the proximal policy optimization (PPO) algorithm for generative problems. In particular, we consider how to effectively reduce the action space by including a greedy search algorithm in the learning process. Our experiments demonstrate that our method converges for a relatively large number of actions and learns to generate scenes with predefined design objectives. This approach is placing objects iteratively in the virtual scene. In each step, the network chooses which objects to place and selects positions which result in maximal reward. A high reward is assigned if the last action resulted in desired properties whereas the violation of constraints is penalized. We demonstrate the capability of our method to generate plausible and diverse scenes efficiently by solving indoor planning problems and generating Angry Birds levels.

Hanan Gani, Shariq Farooq Bhat, Muzammal Naseer et al.

Diffusion-based generative models have significantly advanced text-to-image generation but encounter challenges when processing lengthy and intricate text prompts describing complex scenes with multiple objects. While excelling in generating images from short, single-object descriptions, these models often struggle to faithfully capture all the nuanced details within longer and more elaborate textual inputs. In response, we present a novel approach leveraging Large Language Models (LLMs) to extract critical components from text prompts, including bounding box coordinates for foreground objects, detailed textual descriptions for individual objects, and a succinct background context. These components form the foundation of our layout-to-image generation model, which operates in two phases. The initial Global Scene Generation utilizes object layouts and background context to create an initial scene but often falls short in faithfully representing object characteristics as specified in the prompts. To address this limitation, we introduce an Iterative Refinement Scheme that iteratively evaluates and refines box-level content to align them with their textual descriptions, recomposing objects as needed to ensure consistency. Our evaluation on complex prompts featuring multiple objects demonstrates a substantial improvement in recall compared to baseline diffusion models. This is further validated by a user study, underscoring the efficacy of our approach in generating coherent and detailed scenes from intricate textual inputs.

Ildar Gilmutdinov, Ingrid Schloegel, Alois Hinterleitner et al.

Assessing the structure of a building with non-invasive methods is an important problem. One of the possible approaches is to use GeoRadar to examine wall structures by analyzing the data obtained from the scans. We propose a data-driven approach to evaluate the material composition of a wall from its GPR radargrams. In order to generate training data, we use gprMax to model the scanning process. Using simulation data, we use a convolutional neural network to predict the thicknesses and dielectric properties of walls per layer. We evaluate the generalization abilities of the trained model on data collected from real buildings.

Tom Kelly, John Femiani, Peter Wonka

We present WinSyn, a unique dataset and testbed for creating high-quality synthetic data with procedural modeling techniques. The dataset contains high-resolution photographs of windows, selected from locations around the world, with 89,318 individual window crops showcasing diverse geometric and material characteristics. We evaluate a procedural model by training semantic segmentation networks on both synthetic and real images and then comparing their performances on a shared test set of real images. Specifically, we measure the difference in mean Intersection over Union (mIoU) and determine the effective number of real images to match synthetic data's training performance. We design a baseline procedural model as a benchmark and provide 21,290 synthetically generated images. By tuning the procedural model, key factors are identified which significantly influence the model's fidelity in replicating real-world scenarios. Importantly, we highlight the challenge of procedural modeling using current techniques, especially in their ability to replicate the spatial semantics of real-world scenarios. This insight is critical because of the potential of procedural models to bridge to hidden scene aspects such as depth, reflectivity, material properties, and lighting conditions.

Ngan Nguyen, Feng Liang, Dominik Engel et al.

We propose a new microscopy simulation system that can depict atomistic models in a micrograph visual style, similar to results of physical electron microscopy imaging. This system is scalable, able to represent simulation of electron microscopy of tens of viral particles and synthesizes the image faster than previous methods. On top of that, the simulator is differentiable, both its deterministic as well as stochastic stages that form signal and noise representations in the micrograph. This notable property has the capability for solving inverse problems by means of optimization and thus allows for generation of microscopy simulations using the parameter settings estimated from real data. We demonstrate this learning capability through two applications: (1) estimating the parameters of the modulation transfer function defining the detector properties of the simulated and real micrographs, and (2) denoising the real data based on parameters trained from the simulated examples. While current simulators do not support any parameter estimation due to their forward design, we show that the results obtained using estimated parameters are very similar to the results of real micrographs. Additionally, we evaluate the denoising capabilities of our approach and show that the results showed an improvement over state-of-the-art methods. Denoised micrographs exhibit less noise in the tilt-series tomography reconstructions, ultimately reducing the visual dominance of noise in direct volume rendering of microscopy tomograms.

Jian Shi, Michael Birsak, Wenqing Cui et al.

This paper revisits the role of positional embeddings (PEs) within vision transformers (ViTs) from a geometric perspective. We show that PEs are not mere token indices but effectively function as geometric priors that shape the spatial structure of the representation. We introduce token-level diagnostics that measure how multi-view geometric consistency in ViT representation depends on consitent PEs. Through extensive experiments on 14 foundation ViT models, we reveal how PEs influence multi-view geometry and spatial reasoning. Our findings clarify the role of PEs as a causal mechanism that governs spatial structure in ViT representations. Our code is provided in https://github.com/shijianjian/vit-geometry-probes

Habib Slim, Xiang Li, Yuchen Li et al.

In this work, we present 3DCoMPaT$^{++}$, a multimodal 2D/3D dataset with 160 million rendered views of more than 10 million stylized 3D shapes carefully annotated at the part-instance level, alongside matching RGB point clouds, 3D textured meshes, depth maps, and segmentation masks. 3DCoMPaT$^{++}$ covers 41 shape categories, 275 fine-grained part categories, and 293 fine-grained material classes that can be compositionally applied to parts of 3D objects. We render a subset of one million stylized shapes from four equally spaced views as well as four randomized views, leading to a total of 160 million renderings. Parts are segmented at the instance level, with coarse-grained and fine-grained semantic levels. We introduce a new task, called Grounded CoMPaT Recognition (GCR), to collectively recognize and ground compositions of materials on parts of 3D objects. Additionally, we report the outcomes of a data challenge organized at CVPR2023, showcasing the winning method's utilization of a modified PointNet$^{++}$ model trained on 6D inputs, and exploring alternative techniques for GCR enhancement. We hope our work will help ease future research on compositional 3D Vision.

Jiraphon Yenphraphai, Jianqi Chen, Jian Wang et al.

Current video-to-4D methods struggle with complex topology changes, transparent materials, thin structures, and inner surfaces. We present Helix4D, a dynamic mesh generation framework by inheriting the expressive representation of Trellis2, adapting it from image-to-3D to video-conditioned 4D generation. Our design arises from two key questions: (a) how to enable Trellis2's frame-local attention to share information across frames while preserving its pretrained quality on rare cases such as transparent objects and inner surfaces, and (b) how to inject temporal information into a purely 3D positional encoding without breaking pretrained capabilities. We address (a) with a sliding-window cross-frame attention and anchor on the first frame. The first frame is generated by the base Trellis2 model and injected into our model, letting it inherit Trellis2's quality in rare cases through cross-frame attention. We address (b) with a 4D temporal encoding that repurposes redundant low-frequency spatial RoPE bands for time, extending the encoding from 3D with no additional parameters. Extensive experiments show the effectiveness of Helix4D for high-quality dynamic mesh generation on ActionBench and our own challenging complex dynamics set.

Abdelrahman Eldesokey, Peter Wonka

We propose a diffusion-based approach for Text-to-Image (T2I) generation with interactive 3D layout control. Layout control has been widely studied to alleviate the shortcomings of T2I diffusion models in understanding objects' placement and relationships from text descriptions. Nevertheless, existing approaches for layout control are limited to 2D layouts, require the user to provide a static layout beforehand, and fail to preserve generated images under layout changes. This makes these approaches unsuitable for applications that require 3D object-wise control and iterative refinements, e.g., interior design and complex scene generation. To this end, we leverage the recent advancements in depth-conditioned T2I models and propose a novel approach for interactive 3D layout control. We replace the traditional 2D boxes used in layout control with 3D boxes. Furthermore, we revamp the T2I task as a multi-stage generation process, where at each stage, the user can insert, change, and move an object in 3D while preserving objects from earlier stages. We achieve this through our proposed Dynamic Self-Attention (DSA) module and the consistent 3D object translation strategy. Experiments show that our approach can generate complicated scenes based on 3D layouts, boosting the object generation success rate over the standard depth-conditioned T2I methods by 2x. Moreover, it outperforms other methods in comparison in preserving objects under layout changes. Project Page: \url{https://abdo-eldesokey.github.io/build-a-scene/}

Jian Shi, Zhenyu Li, Peter Wonka

We introduce \textit{ImmersePro}, an innovative framework specifically designed to transform single-view videos into stereo videos. This framework utilizes a novel dual-branch architecture comprising a disparity branch and a context branch on video data by leveraging spatial-temporal attention mechanisms. \textit{ImmersePro} employs implicit disparity guidance, enabling the generation of stereo pairs from video sequences without the need for explicit disparity maps, thus reducing potential errors associated with disparity estimation models. In addition to the technical advancements, we introduce the YouTube-SBS dataset, a comprehensive collection of 423 stereo videos sourced from YouTube. This dataset is unprecedented in its scale, featuring over 7 million stereo pairs, and is designed to facilitate training and benchmarking of stereo video generation models. Our experiments demonstrate the effectiveness of \textit{ImmersePro} in producing high-quality stereo videos, offering significant improvements over existing methods. Compared to the best competitor stereo-from-mono we quantitatively improve the results by 11.76\% (L1), 6.39\% (SSIM), and 5.10\% (PSNR).

Jinjie Mai, Chaoyang Wang, Guocheng Gordon Qian et al.

While image editing has advanced rapidly, video editing remains less explored, facing challenges in consistency, control, and generalization. We study the design space of data, architecture, and control, and introduce \emph{EasyV2V}, a simple and effective framework for instruction-based video editing. On the data side, we compose existing experts with fast inverses to build diverse video pairs, lift image edit pairs into videos via single-frame supervision and pseudo pairs with shared affine motion, mine dense-captioned clips for video pairs, and add transition supervision to teach how edits unfold. On the model side, we observe that pretrained text-to-video models possess editing capability, motivating a simplified design. Simple sequence concatenation for conditioning with light LoRA fine-tuning suffices to train a strong model. For control, we unify spatiotemporal control via a single mask mechanism and support optional reference images. Overall, EasyV2V works with flexible inputs, e.g., video+text, video+mask+text, video+mask+reference+text, and achieves state-of-the-art video editing results, surpassing concurrent and commercial systems. Project page: https://snap-research.github.io/easyv2v/

Mykola Lavreniuk, Shariq Farooq Bhat, Matthias Müller et al.

This work presents the network architecture EVP (Enhanced Visual Perception). EVP builds on the previous work VPD which paved the way to use the Stable Diffusion network for computer vision tasks. We propose two major enhancements. First, we develop the Inverse Multi-Attentive Feature Refinement (IMAFR) module which enhances feature learning capabilities by aggregating spatial information from higher pyramid levels. Second, we propose a novel image-text alignment module for improved feature extraction of the Stable Diffusion backbone. The resulting architecture is suitable for a wide variety of tasks and we demonstrate its performance in the context of single-image depth estimation with a specialized decoder using classification-based bins and referring segmentation with an off-the-shelf decoder. Comprehensive experiments conducted on established datasets show that EVP achieves state-of-the-art results in single-image depth estimation for indoor (NYU Depth v2, 11.8% RMSE improvement over VPD) and outdoor (KITTI) environments, as well as referring segmentation (RefCOCO, 2.53 IoU improvement over ReLA). The code and pre-trained models are publicly available at https://github.com/Lavreniuk/EVP.

Zhenyu Li, Aleksandar Cvejic, Zehui Chen et al.

Pairwise human preference prediction is central to evaluating code-generation systems, where quality often depends on task-specific trade-offs beyond functional correctness. While rubric-based LLM judges improve interpretability by decomposing evaluation into explicit criteria, most existing pipelines remain pointwise: they score each response independently and derive preferences by comparing aggregated scores. We show that this design is poorly matched to pairwise code preference prediction and can underperform a strong monolithic judge. We propose CriterAlign, a criterion-centric framework that adapts rubric-based judging to pairwise preference evaluation through direct criterion-level pairwise judgments, tie-driven criterion refinement, swap-consistency filtering, and final pairwise synthesis. We further introduce Human-Preference-Aligned Guidance (HPAG), synthesized offline from training examples by extracting recurring rationale gaps between human preferences and monolithic judge predictions, and injected into the criterion generator, criterion judge, and final judge. On BigCodeReward, CriterAlign improves a Qwen2.5-VL-32B monolithic judge from 60.4% to 66.3% accuracy, with ablations confirming the contributions of pairwise criterion design and HPAG.

Wenqing Cui, Zhenyu Li, Mykola Lavreniuk et al.

Joint estimation of surface normals and depth is essential for holistic 3D scene understanding, yet high-resolution prediction remains difficult due to the trade-off between preserving fine local detail and maintaining global consistency. To address this challenge, we propose the Ultra Resolution Geometry Transformer (URGT), which adapts the Visual Geometry Grounded Transformer (VGGT) into a unified multi-patch transformer for monocular high-resolution depth--normal estimation. A single high-resolution image is partitioned into patches that are augmented with coarse depth and normal priors from pre-trained models, and jointly processed in a single forward pass to predict refined geometric outputs. Global coherence is enforced through cross-patch attention, which enables long-range geometric reasoning and seamless propagation of information across patches within a shared backbone. To further enhance spatial robustness, we introduce a GridMix patch sampling strategy that probabilistically samples grid configurations during training, improving inter-patch consistency and generalization. Our method achieves state-of-the-art results on UnrealStereo4K, jointly improving depth and normal estimation, reducing AbsRel from 0.0582 to 0.0291, RMSE from 2.17 to 1.31, and lowering mean angular error from 23.36 degrees to 18.51 degrees, while producing sharper and more stable geometry. The proposed multi-patch framework also demonstrates strong zero-shot and cross-domain generalization and scales effectively to very high resolutions, offering an efficient and extensible solution for high-quality geometry refinement.

Aymen Mir, Riza Alp Guler, Xiangjun Tang et al.

We present AHOY, a method for reconstructing complete, animatable 3D Gaussian avatars from in-the-wild monocular video despite heavy occlusion. Existing methods assume unoccluded input-a fully visible subject, often in a canonical pose-excluding the vast majority of real-world footage where people are routinely occluded by furniture, objects, or other people. Reconstructing from such footage poses fundamental challenges: large body regions may never be observed, and multi-view supervision per pose is unavailable. We address these challenges with four contributions: (i) a hallucination-as-supervision pipeline that uses identity-finetuned diffusion models to generate dense supervision for previously unobserved body regions; (ii) a two-stage canonical-to-pose-dependent architecture that bootstraps from sparse observations to full pose-dependent Gaussian maps; (iii) a map-pose/LBS-pose decoupling that absorbs multi-view inconsistencies from the generated data; (iv) a head/body split supervision strategy that preserves facial identity. We evaluate on YouTube videos and on multi-view capture data with significant occlusion and demonstrate state-of-the-art reconstruction quality. We also demonstrate that the resulting avatars are robust enough to be animated with novel poses and composited into 3DGS scenes captured using cell-phone video. Our project page is available at https://miraymen.github.io/ahoy/

Boyi Pang, Savva Ignatyev, Vladimir Ippolitov et al.

We suggest a new multi-modal algorithm for joint inference of paired structurally aligned samples with Rectified Flow models. While some existing methods propose a codependent generation process, they do not view the problem of joint generation from a structural alignment perspective. Recent work uses Score Distillation Sampling to generate aligned 3D models, but SDS is known to be time-consuming, prone to mode collapse, and often provides cartoonish results. By contrast, our suggested approach relies on the joint transport of a segment in the sample space, yielding faster computation at inference time. Our approach can be built on top of an arbitrary Rectified Flow model operating on the structured latent space. We show the applicability of our method to the domains of image, video, and 3D shape generation using state-of-the-art baselines and evaluate it against both editing-based and joint inference-based competing approaches. We demonstrate a high degree of structural alignment for the sample pairs obtained with our method and a high visual quality of the samples. Our method improves the state-of-the-art for image and video generation pipelines. For 3D generation, it is able to show comparable quality while working orders of magnitude faster.

Zhenyu Li, Sai Kumar Dwivedi, Filip Maric et al.

Egocentric human motion estimation is essential for AR/VR experiences, yet remains challenging due to limited body coverage from the egocentric viewpoint, frequent occlusions, and scarce labeled data. We present EgoPoseFormer v2, a method that addresses these challenges through two key contributions: (1) a transformer-based model for temporally consistent and spatially grounded body pose estimation, and (2) an auto-labeling system that enables the use of large unlabeled datasets for training. Our model is fully differentiable, introduces identity-conditioned queries, multi-view spatial refinement, causal temporal attention, and supports both keypoints and parametric body representations under a constant compute budget. The auto-labeling system scales learning to tens of millions of unlabeled frames via uncertainty-aware semi-supervised training. The system follows a teacher-student schema to generate pseudo-labels and guide training with uncertainty distillation, enabling the model to generalize to different environments. On the EgoBody3M benchmark, with a 0.8 ms latency on GPU, our model outperforms two state-of-the-art methods by 12.2% and 19.4% in accuracy, and reduces temporal jitter by 22.2% and 51.7%. Furthermore, our auto-labeling system further improves the wrist MPJPE by 13.1%.

Jianqi Chen, Biao Zhang, Xiangjun Tang et al.

6D object pose estimation, which predicts the transformation of an object relative to the camera, remains challenging for unseen objects. Existing approaches typically rely on explicitly constructing feature correspondences between the query image and either the object model or template images. In this work, we propose PoseGAM, a geometry-aware multi-view framework that directly predicts object pose from a query image and multiple template images, eliminating the need for explicit matching. Built upon recent multi-view-based foundation model architectures, the method integrates object geometry information through two complementary mechanisms: explicit point-based geometry and learned features from geometry representation networks. In addition, we construct a large-scale synthetic dataset containing more than 190k objects under diverse environmental conditions to enhance robustness and generalization. Extensive evaluations across multiple benchmarks demonstrate our state-of-the-art performance, yielding an average AR improvement of 5.1% over prior methods and achieving up to 17.6% gains on individual datasets, indicating strong generalization to unseen objects. Project page: https://windvchen.github.io/PoseGAM/ .

Zehao Xia, Yiqun Wang, Zhengda Lu et al.

Creating high-fidelity, animatable 3D avatars from a single image remains a formidable challenge. We identified three desirable attributes of avatar generation: 1) the method should be feed-forward, 2) model a 360° full-head, and 3) should be animation-ready. However, current work addresses only two of the three points simultaneously. To address these limitations, we propose OMEGA-Avatar, the first feed-forward framework that simultaneously generates a generalizable, 360°-complete, and animatable 3D Gaussian head from a single image. Starting from a feed-forward and animatable framework, we address the 360° full-head avatar generation problem with two novel components. First, to overcome poor hair modeling in full-head avatar generation, we introduce a semantic-aware mesh deformation module that integrates multi-view normals to optimize a FLAME head with hair while preserving its topology structure. Second, to enable effective feed-forward decoding of full-head features, we propose a multi-view feature splatting module that constructs a shared canonical UV representation from features across multiple views through differentiable bilinear splatting, hierarchical UV mapping, and visibility-aware fusion. This approach preserves both global structural coherence and local high-frequency details across all viewpoints, ensuring 360° consistency without per-instance optimization. Extensive experiments demonstrate that OMEGA-Avatar achieves state-of-the-art performance, significantly outperforming existing baselines in 360° full-head completeness while robustly preserving identity across different viewpoints.

Xu Han, Biao Zhang, Xiangjun Tang et al.

We present LumiX, a structured diffusion framework for coherent text-to-intrinsic generation. Conditioned on text prompts, LumiX jointly generates a comprehensive set of intrinsic maps (e.g., albedo, irradiance, normal, depth, and final color), providing a structured and physically consistent description of an underlying scene. This is enabled by two key contributions: 1) Query-Broadcast Attention, a mechanism that ensures structural consistency by sharing queries across all maps in each self-attention block. 2) Tensor LoRA, a tensor-based adaptation that parameter-efficiently models cross-map relations for efficient joint training. Together, these designs enable stable joint diffusion training and unified generation of multiple intrinsic properties. Experiments show that LumiX produces coherent and physically meaningful results, achieving 23% higher alignment and a better preference score (0.19 vs. -0.41) compared to the state of the art, and it can also perform image-conditioned intrinsic decomposition within the same framework.

Xiangjun Tang, Biao Zhang, Peter Wonka

Generating realistic human geometry animations remains a challenging task, as it requires modeling natural clothing dynamics with fine-grained geometric details under limited data. To address these challenges, we propose two novel designs. First, we propose a compact distribution-based latent representation that enables efficient and high-quality geometry generation. We improve upon previous work by establishing a more uniform mapping between SMPL and avatar geometries. Second, we introduce a generative animation model that fully exploits the diversity of limited motion data. We focus on short-term transitions while maintaining long-term consistency through an identity-conditioned design. These two designs formulate our method as a two-stage framework: the first stage learns a latent space, while the second learns to generate animations within this latent space. We conducted experiments on both our latent space and animation model. We demonstrate that our latent space produces high-fidelity human geometry surpassing previous methods ($90\%$ lower Chamfer Dist.). The animation model synthesizes diverse animations with detailed and natural dynamics ($2.2 \times$ higher user study score), achieving the best results across all evaluation metrics.

Jian Shi, Qian Wang, Zhenyu Li et al.

Generating high-quality stereo videos that mimic human binocular vision requires consistent depth perception and temporal coherence across frames. Despite advances in image and video synthesis using diffusion models, producing high-quality stereo videos remains a challenging task due to the difficulty of maintaining consistent temporal and spatial coherence between left and right views. We introduce StereoCrafter-Zero, a novel framework for zero-shot stereo video generation that leverages video diffusion priors without requiring paired training data. Our key innovations include a noisy restart strategy to initialize stereo-aware latent representations and an iterative refinement process that progressively harmonizes the latent space, addressing issues like temporal flickering and view inconsistencies. In addition, we propose the use of dissolved depth maps to streamline latent space operations by reducing high-frequency depth information. Our comprehensive evaluations, including quantitative metrics and user studies, demonstrate that StereoCrafter-Zero produces high-quality stereo videos with enhanced depth consistency and temporal smoothness, even when depth estimations are imperfect. Our framework is robust and adaptable across various diffusion models, setting a new benchmark for zero-shot stereo video generation and enabling more immersive visual experiences. Our code is in https://github.com/shijianjian/StereoCrafter-Zero.

Biao Zhang, Peter Wonka

We propose a new class of generative diffusion models, called functional diffusion. In contrast to previous work, functional diffusion works on samples that are represented by functions with a continuous domain. Functional diffusion can be seen as an extension of classical diffusion models to an infinite-dimensional domain. Functional diffusion is very versatile as images, videos, audio, 3D shapes, deformations, \etc, can be handled by the same framework with minimal changes. In addition, functional diffusion is especially suited for irregular data or data defined in non-standard domains. In our work, we derive the necessary foundations for functional diffusion and propose a first implementation based on the transformer architecture. We show generative results on complicated signed distance functions and deformation functions defined on 3D surfaces.

Fedor Rodionov, Abdelrahman Eldesokey, Michael Birsak et al.

We introduce FloorplanQA, a diagnostic benchmark for evaluating spatial reasoning in large-language models (LLMs). FloorplanQA is grounded in structured representations of indoor scenes, such as (e.g., kitchens, living rooms, bedrooms, bathrooms, and others), encoded symbolically in JSON or XML layouts. The benchmark covers core spatial tasks, including distance measurement, visibility, path finding, and object placement within constrained spaces. Our results across a variety of frontier open-source and commercial LLMs reveal that while models may succeed in shallow queries, they often fail to respect physical constraints, preserve spatial coherence, though they remain mostly robust to small spatial perturbations. FloorplanQA uncovers a blind spot in today's LLMs: inconsistent reasoning about indoor layouts. We hope this benchmark inspires new work on language models that can accurately infer and manipulate spatial and geometric properties in practical settings.